Daily Papers — 2026-09-23
47 papers on audio, speech, music, and acoustics.
1. BiCFlow-MER: Orchestrating Discriminative and Generative Multimodal Emotion Recognition via Conditional Transport
Authors: Yanbing Wang, Shenyue Wang, Chunyang Yu
Categories: cs.AI, cs.SD
In multimodal emotion recognition (MER), human affective states are inferred by integrating complementary cues from multiple modalities. In audio-text MER, affective cues are often entangled with speaker style and lexical content, while cross-modal disagreement further complicates how the evidence should be integrated. Under conventional discriminative fusion, multimodal evidence is compressed into a terminal prediction, with modality-specific cues and conflict information insufficiently preserved. In large generative affective models, by contrast, affective reasoning is typically embedded in language decoding, leaving emotion evidence implicit and difficult to verify in a structured space. To address these limitations, BiCFlow-MER (Bidirectional Conditional Flow for Multimodal Emotion Recognition) is proposed as a conditional-flow framework in which audio-text MER is formulated as generative evidence transport within a structured emotion space. Within BiCFlow-MER, emotion-oriented evidence is disentangled from speaker-style and lexical-content factors to construct a conflict-aware affective condition. Guided by this condition, each utterance is transported to an explicit emotion-space endpoint through a bidirectional rectified flow. Candidate emotions are jointly verified through adaptive prototype-cloud scoring of the transported endpoint and backward class-to-condition consistency with the original multimodal condition, enabling conflict-aware recognition. BiCFlow-MER is shown to outperform all compared methods across IEMOCAP, MELD, and the zero-shot CASE benchmark. By orchestrating discriminative recognition and generative evidence modeling through conditional transport, BiCFlow-MER defines a new MER paradigm.
2. Neither Silence nor Overlap Is Failure: Intent-Conditioned Evaluation of Turn-Taking in Full-Duplex Spoken Dialogue Models
Authors: Kian Shamsaie, Iman Modarressi
Categories: cs.CL, cs.AI, cs.HC, cs.SD
Benchmarks for full-duplex spoken dialogue models score turn-taking with binary fixed-window rules that reward immediate response or silence by completeness of the prior turn. We argue that the appropriateness of a response offset, whether delayed silence or anticipatory overlap, is conditional on the speaker’s latent intent, identifiable only from that speaker’s behavior. We introduce TACT, a benchmark of 9,728 episodes and 73.2 hours from five dyadic corpora; each episode carries dialogue history, a per-speaker memory profile, and an annotator-derived posterior over six intent classes. Scoring replaces binary windows with a strictly proper threshold-weighted continuous ranked probability score whose weights are intent-conditioned timing kernels fitted to human floor-transfer-offset distributions, proving boundedness, consistency, and binary reduction. Across eleven systems the best model reaches 0.47 against a human topline of 0.86, is nearly invariant to speaker profiles, and TACT agrees with human judgments at Spearman 0.81 versus 0.46 for binary metrics.
3. PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMs
Authors: Zhiqi Ai, Han Cheng, Shiyi Mu, Yongjin Zhou, Shugong Xu
Categories: cs.CL, cs.SD
Contextual biasing improves rare-word recognition in speech large language models (SpeechLLMs), but efficiently exploiting large bias lists remains challenging. We propose PTC-Bias, a two-stage framework based on phoneme-level temporal competition. At the prefill stage, PTC Retrieval performs frame-synchronous phoneme decoding and temporal competition among candidate pronunciations, producing a compact bias-word shortlist and corresponding speech intervals. After SpeechLLM decoding, PTC Correction conducts a second local competition between the retrieved candidates and mismatched transcript spans within these intervals. Selective correction reduces near-homophone and word-segmentation errors while preserving correct transcriptions. Both stages share the same phoneme posteriors and require no additional SpeechLLM forward pass. Experiments on LibriSpeech show consistent gains across two SpeechLLMs and bias lists of up to 2000 words. With Prompt-SLAM-ASR-7B and 2000 bias words, PTC-Bias reduces B-WER by 23.4%/23.9% relative to CTC-Filter on test-clean/test-other, while keeping U-WER nearly unchanged.
4. Temporal Taxation Compounds Under Post-Training Compression of Whisper Models
Authors: Srishti Ginjala, Eric Fosler-Lussier, Christopher W. Myers, Srinivasan Parthasarathy
Categories: cs.CL, cs.SD
Automatic speech recognition models are audited for demographic fairness at full precision, yet the models that ship to production have been quantized, pruned, and distilled. We ask whether post-training weight compression, which alters model weights rather than the audio signal or its feature representation, redistributes error burden across demographic groups. Across the Whisper family on Fair-Speech, Common Voice 25, and AfriSpeech-200, 50% Wanda pruning of Whisper-large-v3 sharply widens the Black/AA-vs-Asian temporal-taxation differential on Fair-Speech: the absolute word-error-rate gap between the worst- and best-served groups more than doubles; at an assumed cost of five seconds of correction effort per transcription error this is a rise from 30 to 64 seconds of correction time per minute of speech. This +111% relative increase is invariant to the assumed per-error cost, survives an audio-quality control, and is only partly mitigated by beam-search decoding, which still leaves an +86% increase. At edge model size, INT4 HQQ quantization compounds catastrophic transcript loops on West African accents by factors of five to seven. Distillation, by contrast, narrows demographic gaps in 21 of 27 evaluated settings (teacher-student pair, precision, and dataset), with the exceptions concentrated on a single model pair. We cast the temporal-taxation construct of Choi and Choi (2025) as a quantitative metric, and show that single-snapshot fairness audits on full-precision models do not capture the deployment-time burden that compression places on already-marginalized speakers.
5. Realtime-Venus: A full-duplex interaction system with asynchronous delegation
Authors: Ant Group
Categories: cs.CV, eess.AS
Natural interaction in digital and physical environments requires continuous perception and timely responses. Spoken dialogue relies on acoustic and linguistic cues, while video interaction also requires grounding the conversation in evolving visual context. We present Realtime-Venus, a proactive full-duplex interaction system with two separately trained 9B models: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for spoken interaction. Each model serves as a complete conversational frontend, integrating continuous perception, conversational control, and native speech generation through a shared causal timeline for user inputs, model outputs, and delegation events. A dual-loop runtime coordinates live interaction with background reasoning and tool execution. Foreground interaction continues while Realtime-Venus-Harness executes tasks asynchronously and returns results for integration into the ongoing dialogue. Both models follow a common post-training recipe combining offline understanding, proactive full-duplex trajectories, and delegation workflows. Among the evaluated online models, Realtime-Venus-Omni achieves the highest scores on six of eight video benchmarks, including StreamingBench (70.2%), OVO-Bench (64.7%), and Daily-Omni (81.3%). Across eight audio understanding and spoken question answering benchmarks, Realtime-Venus-Audio leads the compared models on MMAU (78.0%), MMAU-Pro (63.2%), Llama Questions (83.8%), and Speech CMMLU (67.8%), while matching the best VoiceBench AlpacaEval score of 4.81. On Full-Duplex-Bench v1.5, Realtime-Venus-Audio responds to 75% of user interruptions and achieves continuation rates of 97%, 88%, and 86% under backchannels, other-directed speech, and background speech, respectively, exceeding Gemini 3.1 Live and GPT-4o on all three continuation metrics.
6. Intervention, Not Shared Latents: Blocking Visual Shortcuts in Audio-Video Generation
Authors: Jian Xu, Delu Zeng, John Paisley
Categories: cs.LG, cs.GR, cs.SD
Joint audio–video (AV) generators are trained on data in which \emph{what an event looks like} and \emph{what it sounds like} are spuriously correlated. We present a \emph{controlled causal study} of the resulting failure mode. In an AV structural causal model where the audio is, by construction, independent of the video’s nuisance appearance, models that let audio read video directly—through cross-attention or a shared latent—learn a \emph{visual shortcut}: they predict sound from appearance rather than the causal event and, when the appearance–event correlation is broken at test time, synthesize the wrong event’s sound. Crucially, the popular remedy of routing both modalities through a \emph{shared common-cause latent} does \emph{not} fix this—a bottleneck, an unsupervised shared/private factorization, and a faithful shared-prior model all grab the appearance proxy and fail like the direct model. Blocking the shortcut instead requires an \emph{intervention on the nuisance}: under the stated assumptions we prove that counterfactual invariance is necessary and sufficient to identify the causal predictor, and we verify the mechanism from feature-vector SCMs to procedural pixel video, real images with spectrogram audio, moving real digits, and a conditional generator. On a \emph{real, pretrained} V2A generator (MMAudio), an input-intervention test shows the model is far from invariant to sound-irrelevant edits, though a generic-noise control reveals it is broadly input-brittle rather than specifically colour-shortcutting—clean isolation of the shortcut needs the controlled confounds our synthetic studies provide. We characterize \emph{when} the shortcut occurs, compare the objective against supervised counterfactual augmentation, and isolate the \emph{unknown-nuisance} regime—where the intervention cannot be applied—as the central open problem.
7. Anomaly-Free Self-Optimization via AUC Bounds
Authors: Kevin Wilkinghoff, Zheng-Hua Tan
Categories: cs.LG, eess.AS
Anomalies are rare, and anomalous data are often unavailable during development, making it difficult to determine which anomaly detection models and configurations will generalize to unseen anomalies. Recent approaches address this challenge by generating pseudo-anomalies and using bounds on the achievable area under the ROC curve (AUC) to select the optimal configuration from a finite set of candidates. Instead, we use the AUC bound as a differentiable, anomaly-free objective for directly optimizing continuous parameters of anomaly detection systems. We demonstrate this framework by optimizing ensemble weights and introducing a learnable score-rescaling mechanism that adapts pseudo-anomaly scores, enabling optimization beyond a predefined candidate set. Experiments across multiple datasets and embedding models show that AUC-bound optimization achieves significant performance gains over conventional model selection and prior development-set-based parameter selection. The results further show that direct optimization is less sensitive to the choice of pseudo-anomaly construction.
8. Lend me an Ear: Speech Enhancement Using a Robotic Arm with a Microphone Array
Authors: Zachary Turcotte, François Grondin
Categories: cs.RO, cs.SD
Speech enhancement performance degrades significantly in noisy environments, limiting the deployment of speech-controlled technologies in industrial settings, such as manufacturing plants. Existing speech enhancement solutions primarily rely on advanced digital signal processing techniques, deep learning methods, or complex software optimization approaches. This paper introduces a novel speech enhancement robotic platform that can reconfigure the geometry of a microphone array and adapt to changing acoustic conditions. A sixteen-microphone array is mounted on a robotic arm manipulator with seven degrees of freedom. The microphones are divided into four groups of four, including one group positioned near the end-effector. The system reconfigures the array by adjusting the manipulator joint angles to place the end-effector microphones closer to the target speaker, thereby improving the reference signal quality. This proposed system is a multimodal sensing, reconfigurable audio capture device that integrates sound source localization techniques, computer vision, inverse kinematics, minimum variance distortionless response beamformer, and time-frequency masking using a deep neural network. Experimental results suggest that this approach outperforms other traditional recording configurations, achieving a higher average scale-invariant signal-to-distortion ratio and lower average word error rate across multiple input signal-to-noise ratio conditions.
9. ASR ensembling for phoneme intelligibility evaluation of speech anonymizers
Authors: Victor Ménestrel, Sebastian Möller, Slim Ouni, Dorothea Kolossa
Categories: cs.SD
We present the first phoneme-level intelligibility evaluation of speech anonymizers, assessing the performance of ASR-ensemble-based metrics against measured intelligibility from a crowdsourced listening test. Our results show that simple hard-voting ASR metric reaches correlations above 0.9 with human ratings when aggregated by feature, test-type, or condition, provided that multiple ASR models are combined; evaluating stimuli with and without a carrier sentence further improves the correlation at the stimulus level. However, posterior-probability-based confidence metrics bring no gain, which can be traced back to the insufficient calibration of the state-of-the-art open ASR models that were utilized here. All data, code, and evaluation tools are released as open source.
10. Statistical Models for Automatic Fingering-Annotated Piano Sheet Music Transcription
Authors: Daniel Penner, Abram Hindle
Categories: cs.SD
Machine learning tools have significantly aided automatic piano music transcription; however, this domain has focused primarily on accurately predicting the pitches and timings of played notes. To produce sheet music for the piano, notes must be separated into two staves, one for each hand, and good sheet music often contains fingering annotations to guide the player when sight-reading or learning fast or complex pieces. We propose 8 statistical approaches for combined hand and fingering annotation of transcribed piano notes, including baseline hidden Markov models, rule-based methods, a synthesis of existing approaches, and N-gram language models. Furthermore, we develop a pipeline for complete transcription from piano audio to fingering-annotated sheet music. Evaluations with the PIG dataset demonstrate that our Synthesis model achieves a hand separation accuracy of 90.8\% and a joint hand and finger annotation accuracy of 56.6\%. These approaches serve as a new baseline for further research into this problem, while our pipeline demonstrates the feasibility of a combined system for automated note transcription, hand separation, and fingering annotation.
11. Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speech
Authors: Hyoeun Kim, Yujun Lee, Kyuhong Shim
Categories: cs.SD, cs.AI
Recent zero-shot text-to-speech (ZS-TTS) systems can reproduce a speaker’s voice with high fidelity from only a few seconds of reference speech, raising concerns over unauthorized voice cloning and impersonation. Speaker identity unlearning has recently emerged as an approach to selectively suppress this capability for speakers who opt out while preserving synthesis capability for other speakers. Although existing approaches reduce speaker similarity, preventing re-identification often faces severe degradation of speech quality. Motivated by this observation, we propose GUARD, a lightweight speaker identity unlearning framework that combines a learned speaker gate with speaker-agnostic activation steering on a frozen TTS backbone. The steering vectors are optimized using group-relative reward optimization to shift outputs from forget speakers toward population-level impostor similarity while preserving intelligibility and speech naturalness. On CosyVoice2, GUARD reduces forget-speaker similarity from 0.541 to 0.103 and re-identification accuracy in a 150-speaker gallery from 73.5% to 0.5%, while preserving retain-speaker reproduction. The results demonstrate that similarity reduction alone may not fully characterize successful speaker identity unlearning and highlight re-identification as a complementary criterion for its evaluation.
12. OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents
Authors: Ruixun Liu, Yuxuan Wang, Jiacheng Xie, Yuhuan You, Donghua Cai et al.
Categories: cs.SD, cs.AI
Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challenging for embodied agents. In particular, it is still unclear how to effectively evaluate and model spatial audio understanding in embodied settings. To address this gap, we introduce \textbf{OmniEchoBench}, a unified benchmark for spatial audio-visual perception and audio-vision-language navigation. OmniEchoBench comprises six tasks over 197 real-world spatial audio-visual scenes, 2,972 question-answer pairs, and 900 navigation samples with first-order ambisonics (FOA) audio collected from 30 real-world environments. To enable scalable training supervision, we develop a controllable rendering pipeline for spatial audio. It preserves geometric consistency among sound sources, visual observations, and agent trajectories. Building on this, we propose \textbf{OmniEcho}, a spatially aware omni-modal model. It introduces an FOA spatial encoder alongside a pretrained semantic audio pathway. Extensive experiments show that OmniEcho achieves state-of-the-art performance on spatial audio-visual perception. For our sound-guided navigation, OmniEcho reaches a performance level close to that of traditional vision-language navigation. These results demonstrate that spatial audio can serve as a valuable signal for embodied scene reasoning and navigation, while also highlighting fine-grained spatial localization and distance estimation as important open challenges. Our code and data will be available in https://github.com/PKU-VaLuE-Lab/OmniEcho/tree/main
13. Passing: An Endless Journey through Reconstructed Spacetime with AI-Generated Sound
Authors: Akira Takahashi, Chihiro Nagashima, Zhi Zhong, Shusuke Takahashi, Yuki Mitsufuji
Categories: cs.SD, cs.AI
This paper introduces Passing, an interactive audiovisual installation that generates an endless journey from a single continuous monorail-window recording by reconstructing it as a spatiotemporal volume. Rather than replaying the footage linearly, the work resamples its spatial and temporal structure along nonlinear trajectories, producing a continuously passing landscape whose depth, speed, and temporal order become unstable. A camera-based viewer-presence detection system estimates whether a viewer is present in the viewing zone and uses this presence state to influence transitions among rendered video sequences. The resulting video stream is fed into SpecMaskFoley, a real-time video-to-audio synthesis model that generates a synchronized soundscape for the reconfigured image. The model is not used to reconstruct an objectively correct soundtrack, but functions as a speculative listener, proposing a possible auditory interpretation of a world whose conventional spatial and temporal premises have been disrupted. Passing distributes creative agency across the artist, who defines the rules of spacetime reconstruction; the AI model, which interprets the emergent visual flow as sound; and the audience, whose embodied presence influences the audiovisual trajectory. Through this structure, the work investigates how authorship and listening may be negotiated among human intention, machine inference, and audience interpretation. Artwork page: https://ryufurusawa.com/passing
14. Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models
Authors: Kian Shamsaie, Iman Modarressi
Categories: cs.SD, cs.AI, cs.CL, cs.HC
End-to-end speech-to-speech dialogue models listen and speak simultaneously, so a continuously open acoustic channel is exposed to adversarial manipulation. We formalize imperceptible attacks on full-duplex agents as optimization over additive perturbations confined beneath the psychoacoustic masking threshold of the carrier speech, under three goals: targeted semantic hijacking, response suppression, and policy jailbreaking. Against an undefended Moshi-style agent, white-box attacks succeed in up to 91.7% of trials. We then introduce psychoacoustically aligned latent smoothing (PALS), which injects anisotropic Gaussian noise shaped by local codebook covariance at the residual-vector-quantized latent interface, with input noise shaped by the masking threshold constraining the attacker and trained by a Kullback–Leibler consistency objective. Deployed with no inference-time cost, PALS reduces hijack to 8.3%, mute to 11.2%, and jailbreak to 9.1% at clean quality within 2.3%. A Monte Carlo-smoothed variant certifies an ellipsoidal latent radius up to 0.616, a guaranteed floor that the empirical robustness far exceeds.
15. BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge
Authors: Prakriti Subedi, Howard Prioleau, Saurav K Aryal
Categories: cs.SD, cs.CL
We describe our submission to the Unsupervised Speech in the Wild (UPS) Challenge at Interspeech 2026, a bidirectional Mamba-2 (BiMamba2) encoder trained with masked discrete-unit prediction following the HuBERT-style paradigm. The 47.88M-parameter model is trained on 250 hours of speech across 67 languages from the MLCommons Unsupervised People’s Speech dataset, with no labeled data. The objective combines masked k-means pseudo-label prediction with language identification supervision and VICReg regularization. On official evaluation, the system achieves an Adjusted Rand Index of 0.735, exceeding four baselines on speaker clustering. Language identification macro-F1 (0.073) and character error rate (0.870) remain below supervised baselines. We analyze a local-official discrepancy in metric scale and checkpoint ranking, highlighting limitations of in-distribution diagnostics for predicting Dynabench probe outcomes.
16. Causal Tracing of Audio-Text Fusion in Large Audio Language Models
Authors: Wei-Chih Chen, Chien-yu Huang, Hung-yi Lee
Categories: cs.SD, cs.CL
Despite the strong performance of large audio language models (LALMs) in various tasks, exactly how and where they integrate acoustic features with textual context remains unclear. We adapt causal tracing to investigate the internal information flow of LALMs during audio comprehension. By conducting layer-wise and token-wise analyses across DeSTA, Qwen, and Voxtral, we evaluate the causal effects of individual hidden states. Layer-wise analysis identifies different fusion strategies, from progressive integration in DeSTA to abrupt late-stage fusion in Qwen. Token-wise analysis shows that the final sequence token acts as an informational bottleneck where the network decisively retrieves relevant information from the audio. We also observe an attention-like query mechanism at intermediate token positions that triggers the model to pull task-relevant audio context. These findings provide a clear characterization of when and where multi-modal integration occurs within LALMs.
17. Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding
Authors: Kaiyang Li, Shaobo Han, Yue Tian, Shihao Ji
Categories: cs.SD, cs.CL
Audio-language models (ALMs) integrate acoustic perception with the knowledge encoded in language models, enabling contextual understanding of auditory events. Making these capabilities practical on devices with limited memory and computation motivates our focus on small ALMs with fewer than 200M parameters. We introduce a recipe that brings together architecture, data, and three-stage training to build Mizar, a 159.3M-parameter ALM. Its architecture connects a compact CED-Small audio encoder to SmolLM2-135M through a frequency-merging mapper. With supervision drawn from ReasonAQA, AudioMCQ, and AVQA, the model undergoes three training stages: audio-language alignment (Stage 1), audio-dependent fine-tuning (Stage 2), and post-training (Stage 3) aimed at strengthening weak skills while retaining learned capabilities. Across five random seeds, Mizar achieves mean accuracies of 52.92% on MMAU, 42.42% on MMAR, and 36.02% on ADQA-clean, surpassing the previous best-performing ALM below 200M parameters on all three benchmarks. It also supports local inference on a single CPU: on questions from the MMAU benchmark, the mean latency from opening the audio file to generating a complete answer is 1.09 seconds. Code and checkpoints are available at https://github.com/KaiyangLi1992/Mizar_159M.
18. Quieter Than the Room: Representation Drift and Task Robustness in Speech Encoders
Authors: Vsevolod Kovalev, Pranay Manocha
Categories: cs.SD, cs.CL
Non-speech interference can change a speech representation without causing comparable task loss. We test eight frozen encoders on four tasks, adding non-speech sounds throughout recordings, during speech, or in pauses. Under whole-recording interference, embedding drift tracks task loss across seven sounds, with mean Spearman correlations of 0.81-0.88. Moving the same sound between speech and pauses changes this pattern. At quiet to moderate levels, pause interference produces larger drift, while speech interference usually causes greater loss on intent recognition, speaker verification and speech recognition. Emotion recognition shows a weaker placement effect. Pause interference also changes speech-frame representations beyond the injected region. Even below the estimated recording background, interference can change embeddings as much as repeated speech takes do. Drift helps rank the effects of different sounds, but larger drift does not consistently indicate greater task loss.
19. Reward-Tilted On-Policy Distillation for Acoustic Grounding in Audio-Language Models
Authors: Kaiyang Li, Shaobo Han, Yue Tian, Shihao Ji
Categories: cs.SD, cs.CL
Audio-language models (ALMs) can exploit textual shortcuts to answer questions while overlooking acoustic evidence, weakening audio understanding. On-policy distillation (OPD) trains compact ALMs by supervising student-generated responses with teacher predictions, but does not explicitly distinguish acoustic support from linguistic predictability. We propose Reward-Tilted On-Policy Distillation (RT-OPD) to strengthen acoustic grounding. Given the same question and student-generated text, a frozen teacher predicts the next token with and without audio inputs. Their log-probability contrast defines a reward that reshapes the teacher distribution for reverse-KL distillation, emphasizing the additional evidence provided by audio. Across two compact students and three benchmarks, RT-OPD consistently outperforms Vanilla OPD. Experiments with silenced and replacement audio further suggest that RT-OPD strengthens the student’s reliance on acoustic evidence. Our 3B model achieves 72.72% accuracy on MMAU, the highest among the compared 3B models and competitive with several 7B and 8B models. Code and model checkpoints are available at https://github.com/KaiyangLi1992/RT-OPD.
20. When Entanglement Lower-Bounds Disparity: Auditing and Repairing Demographic Fairness in Audio Understanding Models
Authors: Kian Shamsaie, Iman Modarressi
Categories: cs.SD, cs.CL
Speech technology penalizes some voices: recognition errs nearly twice as often for Black speakers, and accuracy declines for second-language accents and older speakers. We introduce TRIAD, an audit grid crossing 120 texts, 24 rendered demographic voice profiles (gender, age band, accent), and ten expressive styles via controllable text-to-speech, isolating perceived demographic attributes from content and affect. For ten open-weights encoders we define axis-fidelity functionals, principal-angle leakage between axis subspaces, and group-conditional gaps; a proposition proves that average probe disparity grows with the same aggregate voice-semantic leakage $Λ$ we measure, and a corollary shows that peak leakage forces worst-case disparity inside an active region. The measured mean-square probe disparity tracks $Λ$ (Pearson r = 0.93), and a black-box protocol exposes the same signature in two closed-source models. ORCA, an adapter combining axis-specific contrastive heads, an orthogonality penalty, and group-balanced sampling, cuts leakage 72% and roughly halves the gaps.
21. Sona: Personalized Soundscape Mediation to Support People with Sound Sensitivity
Authors: Jeremy Zhengqi Huang, Emani Hicks, Sidharth, Gillian R. Hayes, Dhruv Jain
Categories: cs.SD, cs.HC
People with sound sensitivity (PWSS) often manage distressing sounds with earplugs and noise-canceling headphones that broadly suppress their surroundings, limiting access to useful auditory cues. We present Sona, a mobile system for personalized, real-time soundscape mediation, informed by prior sound sensitivity research and an online survey of 68 PWSS. Sona selectively attenuates multiple overlapping user-chosen sounds at adjustable strength, suggests targets from ambient sound recognition, and lets users add custom targets from short recordings without retraining the model. In an in-situ evaluation with ten PWSS, participants reported that Sona made their soundscapes more manageable. The study also surfaced uneven attenuation across sound type and context, tensions between managing filters and attending to ongoing activities, and difficulty interpreting personalization outcomes. These findings highlight the need to design for the quality of the residual soundscape, balance user control with interaction demands, and support guided, interpretable personalization.
22. EvoAudio: Recursive Self-Improvement for Audio Understanding
Authors: Yuxiang Wang, Shengbo Cai, Yingda Shen, Ming-Hao Hsu, Qinke Ni et al.
Categories: cs.SD, cs.LG
Audio language models understand what is said far better than how it sounds. Closing this gap takes more than data. Detailed acoustic annotation is costly, labels from stronger models inherit their errors and limits, and fixed data cannot adapt as the learner improves. We therefore propose EvoAudio, a recursive self-improvement system for audio understanding. To our knowledge, it is the first to evolve the model, waveforms, questions, and difficulty in one closed loop. EvoAudio uses the current model’s performance to set the focus and difficulty of the next training data. A library of audio tools then constructs questions whose answers follow from how the audio was made, providing verifiable supervision without new human annotation. Reinforcement learning updates the model, and validation decides whether it enters the next evolution round. Across 13 rounds, EvoAudio improves five models with different audio encoders and language backbones on MMSU, MMAU-Pro, and MMAR. It achieves the highest average for every backbone, raising overall performance by up to 6.3 points. The improvement unfolds over successive rounds, with each stronger model starting the next round.
23. Do Audio Representations Compose Additively?
Authors: Chenhao Xue, Zhijin Guo, Joyraj Chakraborty, Martin Reed, Nikolaos Thomos
Categories: cs.SD, cs.MM
Compositionality, the ability to represent complex acoustic scenes as combinations of simpler sound sources, is central to auditory perception and classical additive signal models. Still, it remains unclear whether modern pre-trained audio representations internalize additive structure without compositional supervision. Existing evaluation frameworks of audio compositional reasoning largely focus on cross-modal audio-text alignment, leaving open whether audio representations themselves exhibit additive compositional structure independent of text grounding, analogous to vector arithmetic in word representations. To investigate this, we adopt a two-step diagnostic for frozen audio representations. First, we quantify linear alignment between representations and sound source labels using canonical correlation analysis. Second, we test additive compositional generalization via leave-one-combination-out reconstruction, grouping clips by exact source-label set, averaging their representations, and predicting held-out means from per-source contributions fitted only on training combinations. With larger combination holdouts, CLAP outperforms the permuted and label-overlap baselines on FSD50K, while the speech models do not outperform the label-overlap baseline. We examine representations generated by Wav2Vec2, HuBERT, and CLAP on FSD50K and CHiME-Home datasets. All three models show consistently higher linear correlation and more accurate leave-one-combination-out reconstructions than the permuted baselines. However, only CLAP shows large cosine similarity gains, which could be associated with its training on many kinds of audio and text. Finally, we note that all three models exhibit reconstruction residuals, revealing limits of additive compositionality such as nonlinear or non-compositional audio structure.
24. A multi-resolution spectrogram approach for estimating the physical parameters of a plate reverb
Authors: Jared Lipkin, Meiying Chen, Benjamin R. Thompson, Andrea Cogliati, David A. Anderson et al.
Categories: eess.AS
The ResNet-18 image classification model is employed to determine the physical parameters of a plate reverb from a recording of the impulse response. The model is adapted to derive parameters using normalized and downsampled multi-resolution spectrograms computed from the provided impulse responses (IRs). To refine the prediction of the output location, the spectral phase response is also included as an additional input channel to the network since multiple output locations can give the same magnitude response for high-order resonant modes. On a 5000 IR validation set, our model achieves an average normalized mean squared error (NMSE) of 0.02920 across all parameters, with the lowest average NMSE occurring for parameters yo (0.00228), Ly (0.00347), and xo (0.00574).
25. Beyond DER: Speaker Counting in Crowded End-to-End Diarization
Authors: Lahiru Samarakoon, Hongxu Zhu
Categories: eess.AS
Speaker diarization must solve two problems: counting how many speakers are present in a given conversation, and assigning speech to each one. This becomes harder in crowded conversations with five or more speakers. We evaluate how end-to-end neural diarization models count speakers, and find systematic under-counting in crowded recordings. The standard diarization error rate (DER) hides this failure, because it is duration-weighted and barely penalizes the dropped, low-activity speakers. We therefore also report the Jaccard error rate (JER) and explicit counting metrics. We propose a gated loss that couples speaker existence with frame activity. This loss can be computed in two ways, duration-weighted or speaker-weighted, and the speaker-weighted variant, used as a regularizer, reduces the under-count. On real-world crowded recordings our method clearly improves the counting metrics, lowering JER by about 6% relative and DER by about 9% relative, while leaving sparse recordings unharmed.
26. DriftAudio: Marginal Drifting for Distributional Post-Training of One-Step Text-to-Audio Generators
Authors: Xingyu Chen, Fei Ma, Sipei Zhao
Categories: eess.AS
Recent one-step text-to-audio (TTA) models substantially reduce inference cost, yet their generated distributions can still be improved through post-training. We propose DriftAudio, a distributional post-training method that adapts Drifting to pretrained one-step TTA generators. Applying Drifting condition-wise is challenging under free-form text conditioning, where only one or a few real samples are typically available for a particular condition. DriftAudio instead performs Drifting on the marginal audio distribution while retaining text-conditioned generation. The drifting field is estimated in a frozen audio feature space using resampled real samples, a rolling bank of generated samples, and the current batch of generated samples. The resulting Drifting field provides a detached training target for updating only the generator, keeping the original one-step inference procedure. On AudioCaps, starting from MeanAudio, DriftAudio reduces FAD and FD by 33.9% and 17.6%, respectively, while also improving KL and CLAP. Starting from FdAudio, it further reduces FAD, FD, and KL, with trade-offs in IS and CLAP. These results demonstrate the effectiveness of marginal distributional post-training for one-step TTA generation.
27. Echo Detection in Spatial Room Impulse Responses Measured with Spherical Microphone Arrays Using the Herglotz Wavefunction
Authors: Pierre Massé, Anthony Gallien, Wolfgang Kreuzer, Markus Noisternig
Categories: eess.AS
Early reflections in spatial room impulse responses (SRIRs) measured using spherical microphone arrays (SMAs) play an important role in spatial audio analysis, rendering, and reverberation modeling. Their accurate localization and characterization can facilitate the analysis, processing, and manipulation of measured reverberation fields. This paper proposes a method for detecting and characterizing early reflections based on the Herglotz wavefunction formalism. The measured sound field is represented as a continuous superposition of incident plane waves, from which a localization function is derived in the spherical harmonic domain. An adaptive radial Gaussian fitting procedure is then used to estimate both the directions of arrival (DoAs) and the number of incident reflections within a single analysis frame. The proposed framework is evaluated using simulated and measured SRIRs and compared with conventional steered response power (SRP) and multiple signal classification (MUSIC) localization methods. The results demonstrate improved localization accuracy and more reliable detection of multiple simultaneous reflections, highlighting the potential of the proposed Herglotz-based formulation for the analysis of early reflections in SMA-measured SRIRs.
28. EmphTTS: an emphasis-control TTS with reinforcement learning
Authors: Zirui Li, Rech Silas, Lauri Juvela, Tom Backstrom, Mikko Kurimo
Categories: eess.AS
Generating controllable and human-like emphasis remains an open challenge in text-to-speech, even when explicit emphasis control signals are provided in the text input, limiting the communicative accuracy of synthetic speech in real-world applications. Reinforcement learning has recently shown promise for post-training TTS systems to align with human preference, yet existing methods have not been applied to word-level prosodic control. We present EmphTTS, a non-autoregressive TTS system that applies Group Relative Policy Optimization (GRPO) to the duration predictor with an emphasis localization reward, enabling direct optimization for word-level emphasis. Evaluations show that EmphTTS achieves the best emphasis controllability and performs the best in emphasis objective evaluation. In subjective preference tests, EmphTTS is significantly preferred over synthetic groundtruth and most baselines. Ablation studies show that GRPO improves emphasis realization beyond supervised-finetuning-based duration modeling and simple speaking-rate adjustment, while alleviating the mismatch between the independently trained duration predictor and TTS model.
29. JASPER: Joint Audio and Speech Pre-trained Encoder Representations
Authors: Geeth George, Ameenudeen P E, Hrishikesh H Pillai, Sriram Ganapathy
Categories: eess.AS
Self-supervised learning (SSL) for speech and audio has largely progressed along separate tracks: speech models emphasise time-domain prediction, whereas audio representation learning has focused on time-frequency patterns. This separation creates a compatibility gap, limiting cross-domain generalization. In this work, we introduce JASPER, Joint Audio and Speech Pre-trained Encoder Representations, a framework that augments speech-pretrained models with time-frequency objectives. Specifically, JASPER performs masked prediction of temporal and spectral targets over long audio segments, enabling spectro-temporal representation learning of speech and audio signals. The proposed method consistently outperforms multiple baselines and existing speech/audio encoders on diverse speech, audio, and music tasks, demonstrating the effectiveness of unified spectro-temporal modeling.
30. Neural Field-of-View for Binaural Signal Matching with Wearable Microphone Arrays
Authors: Matan Yifrach, Boaz Rafaely
Categories: eess.AS
The growing use of spatial audio in applications such as augmented and virtual reality has driven the development of binaural reproduction methods for wearable arrays with a limited number of microphones. Binaural signal matching (BSM) is one such method, producing high-quality binaural signals under a diffuse-field assumption, but degrading at high direct-to-reverberant ratios (DRR) where the direct sound dominates. Previous extensions incorporate Field-of-View (FoV) weighting, either with fixed apertures or based on explicit source localization, but these approaches are limited by coarse spatial coverage or reliance on localization estimation accuracy. This paper introduces FoV-BSM-Net, a signal-dependent FoV-BSM formulation that avoids explicit source estimation by learning the FoV parameters end-to-end from the microphone signals using a Convolutional Recurrent Neural Network. The method is evaluated in simulated rooms across varying reverberation conditions, and compared against BSM and a fixed FoV-BSM baseline. Results show that FoV-BSM-Net consistently improves over BSM, with gains that grow with DRR in both binaural NMSE and interaural cue errors, and are further supported by perceptual evaluation showing a substantial advantage over both baselines across low and high DRR conditions.
31. RESTORE: REal-time Steerable Music resTORation and bandwidth Extension via stem disentanglement
Authors: Meiying Chen, Benjamin R. Thompson, Michael C. Heilemann
Categories: eess.AS
Neural methods for audio restoration are typically framed as rigid mappings from degraded inputs to single clean outputs, enforcing decisions about what audio content is removed, and potentially adding unwanted content to the restored signal. Because what constitutes a restored audio signal is subjective, we introduce RESTORE, a framework that formulates audio restoration as a six-source semantic decomposition to allow for real-time interactive user control over the process. By expanding a pretrained HTDemucs backbone, a single forward pass disentangles a degraded mixture into vocals, music, broadband hiss, impulsive transients, and an unmodeled residual, while jointly synthesizing a high-frequency extension. Users may steer the restoration by adjusting stem gains, ensuring generative content remains isolated and auditable. RESTORE improves audio quality on diverse historical recordings compared to baselines,lowering Frechet Audio Distance (FAD) (12.13 VGGish; 0.92 CLAP) and delivering aesthetic steerability (Spearman rho greather than 0.91) at 50x real-time on a single GPU. Code and audio samples are available at https://melissachen15.github.io/restore-audio-demo.
32. Subjective Evaluation of DNN AND Auditory-Model-Based Hearing-Loss Compensation
Authors: Chuan Wen, Brent Nissens, Nele De Poortere, Morgan Thienpont, Matthias Inghels et al.
Categories: eess.AS
Outer-hair-cell (OHC) loss is a primary deficit of sensorineural hearing loss (SNHL), impairing cochlear amplification and frequency selectivity and thereby elevating hearing thresholds. Biophysically-inspired DNN-based hearing-aid (HA) algorithms have been proposed to compensate for OHC deficits and have shown clear benefits in objective speech intelligibility and quality metrics (e.g. HASPI, HASQI). However, comprehensive subjective validation of these benefits in human listeners is still missing. In this work, we present a subjective evaluation of a biophysically-inspired HA model targeting OHC deficits. The cochlear module of an auditory model was individualized based on each listener’s pure-tone audiogram and integrated into a trainable system, which includes the personalized model and a normal-hearing reference model, and the resulting trained HA was evaluated using a Matrix test comparing intelligibility scores for unprocessed and HA-processed noisy speech. The results revealed a significant benefit of the HA model over the unprocessed condition in the range of +1 to +27%, providing behavioral confirmation of the efficacy of the HA model. This study closes the gap between objective and perceptual evidence for this new generation of DNN-based HA algorithms, paving the way for their integration into next-generation DNN-accelerated chips for hearables and hearing aids.
33. A Harness for Synthesizing Diverse Naturalistic Full-Duplex Conversations
Authors: Matthew Sun, Vinay Kothapally, Meng Yu, Chao Huang, Hao Zhang et al.
Categories: eess.AS, cs.AI
Full-duplex dialogue systems, which listen while speaking, must distinguish a completed turn from a pause within a turn and an interruption that requests a turn from a brief acknowledgment or speech addressed to a third party. Yet existing conversational corpora provide limited control over these events and limited labels for their intent. We present a pipeline for synthesizing intent-labeled, two-channel conversational speech from relational event lists. An LLM authors each event’s speaker, text, conversational act, and attachment to an earlier event without predicting absolute timestamps. Events are synthesized independently, aligned with their source text, and placed on a shared clock, so turn-taking landmarks are measured from the rendered signal while silence durations are specified or sampled from turn-taking distributions. The pipeline covers 42 phenomena across eight families in English and Mandarin, derives frame-level system actions from authored intent, and promotes diversity using small, diverse sets of prior examples and batch prompts that request alternatives with self-reported probabilities. Ablations show gains in each targeted diversity dimension. On a four-action label space for taking, holding, releasing, and not holding the conversational floor, a semantic voice-activity detector using only current and past audio reaches start-speaking and start-listening F1 scores of 0.819 and 0.802. When generating its own responses, the full-duplex speech model Moshi takes 0.85 of the reference turns after fine-tuning on the generated corpus, compared with 0.44 before fine-tuning. Its frame-level precision for predicting system-floor occupancy rises from 0.46 to 0.88. With reference context at each step, its frame-level floor F1 rises from 0.893 to 0.962. These results show that controlled synthesis can provide learnable and transferable supervision for full-duplex turn management.
34. Spooftral: Can Voxtral Audio-Language Model Detect Speech Spoofing?
Authors: Avishai Weizman, Yehuda Ben-Shimol, Itshak Lapidot
Categories: eess.AS, cs.CL
Self-supervised learning (SSL) countermeasures (CMs) have shown strong performance in recent years. However, they often show degraded performance while facing unseen spoofing attacks and mismatched conditions. This study examines the Voxtral audio-language model (ALM) framework for spoofing detection, as a step toward combining CM capabilities within the ALM framework. We analyze how Voxtral captures spoofing cues through audio-text processing and propose an instruction-guided approach that uses label-sequence likelihoods to evaluate bonafide and spoofed speech. Experiments on the ASVspoof databases show that without task-specific adaptation, the LLM layers emphasize semantic representations, reducing the separability of spoof-discriminative acoustic cues compared to the Whisper-based audio encoder. Consequently, spoofing-related information becomes less separable after language-model processing. We also applied lightweight adaptation using weight-decomposed low-rank adaptation (DoRA) to the Voxtral model and propose the Spooftral model, achieving an equal error rate (EER) of 4.25% on the ASVspoof5 evaluation set.
35. Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge
Authors: Shangyue Jia, Jingru Ma, Yangzhuo Li, Daoping Luo, Bowen Tian et al.
Categories: eess.AS, cs.CL, cs.SD
Non-verbal vocalizations (NVVs) carry important paralinguistic information but are often omitted by conventional automatic speech recognition (ASR) systems. The ISCSLP NVVSpeech Challenge requires joint transcription of lexical content and 16 NVV categories under limited and highly imbalanced supervision. We present a data-centric NVV-aware ASR pipeline based on cross-dataset label harmonization and a two-stage sampling schedule. We map heterogeneous source labels to the official taxonomy and exclude samples without a reliable mapping. Our schedule first uses square-root category sampling to moderate the long-tailed distribution and then applies uniform-category fine-tuning. On a fixed local validation split, square-root category sampling performs best among the tested single-stage settings. The final two-stage system obtains an official score of 63.86 and ranks fourth in Track 1.
36. A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification
Authors: Christiaan M. Geldenhuys, Thomas R. Niesler
Categories: eess.AS, cs.LG, cs.SD, q-bio.QM
We present a parameter-free episodic evaluation of nearest-centroid classification of elephant vocalisations on fixed pretrained embeddings, for the Elephant Voices (EV) and Linguistic Data Consortium (LDC) datasets. We ask not which embedding yields the best classifier trained on all labelled data, but how the simplest classifier performs as the number of exemplars per class varies. There are no learnable parameters, because each class is modelled as the mean of its support embeddings and each query is assigned to the nearest centroid under squared Euclidean distance. Evaluation covers the fixed Perch (ver. 1), Perch (ver. 2) and HuBERT (base, layer 2) embeddings, alongside mel frequency cepstral coefficient (MFCC) features, $N$-way $k$-shot, under the same stratified $K$-fold cross-validation protocol as the trained classifiers. None of these embedding models was trained to distinguish elephant call types. On the smaller EV dataset the centroid classifier is markedly data-efficient. Using Perch (ver. 1) or Perch (ver. 2) embeddings it overtakes in mean average precision (mAP) the fully-trained logistic regression (LR) baseline from one or two exemplars and the recurrent baseline from two. Over the reduced set of call types on which the strongly-supervised end-to-end baseline was trained, the centroid classifier using Perch (ver. 2) embeddings overtakes that baseline in mAP as well, from two exemplars. On the larger LDC dataset the recurrent baselines retain their advantage for all considered values of $k$. Only LR is overtaken, and only in mAP. Nearest-centroid classification is therefore preferable precisely when exemplars are few and the fixed embedding already separates the call types.
37. Diarization Error Decomposition Under Pause Annotation Ambiguity
Authors: Shota Horiguchi, Marc Delcroix, Naohiro Tawara, Alexis Plaquet
Categories: eess.AS, cs.SD
Speaker diarization evaluation is sensitive to ambiguity in pause annotation, which can inflate diarization error rate (DER) or obscure genuine model errors. We show that morphological closing, which has been used for pause-tolerant diarization evaluation, discards segment-level distinctions. Instead, we propose an exact, overlap-aware decomposition of standard DER into a pause-attributable component, consisting of errors compatible with pause filling, and a residual core component that can serve as a proxy for intrinsic diarization errors. The decomposition leaves DER unchanged, while the pause-attributable and core components vary monotonically with the pause threshold and eventually saturate. Experiments spanning synthetic transformations, annotation mismatch, cross-domain evaluation, and tight-boundary diarization show that the decomposition reveals error sources not apparent from standard DER.
38. Joint Residual Reweighting for Classifier Free Guidance in Flow-Matching Zero-Shot TTS
Authors: Runwu Shi, Yujin Wang, Hongjin Song, Jiang Wang, Yaozhong Kang et al.
Categories: eess.AS, cs.SD
Classifier-free guidance (CFG) is widely used in flow-matching-based zero-shot text-to-speech (TTS), where generation is conditioned on text content and a speech prompt. Standard CFG uses a single guidance weight for their joint conditional effect, while branch-selective guidance emphasizes text or speaker conditioning and can introduce a trade-off between text accuracy and speaker similarity. In this paper, we revisit CFG under independently masked conditions and decompose the guidance field into text, speaker, and joint residuals. We show that condition-specific branch differences couple the joint residual with the corresponding text or speaker residual under a shared weight. Trajectory analysis further shows that the joint residual varies over flow time and contains information that cannot be represented by reweighting the text and speaker residuals alone. Based on these observations, we propose joint residual reweighting, which assigns independent weights to the three residuals. Experiments on F5-TTS, CosyVoice2, and GLM-TTS across three evaluation sets show overall improvements in speaker similarity and text accuracy over the default CFG settings without retraining.
39. Preference Optimization with LALM Feedback for Continuous Autoregressive Non-Verbal Vocalization Generation
Authors: Jingbin Hu, Qirui Zhan, Yuang Cao, Ziyu Zhang, Yunxiang Chen et al.
Categories: eess.AS, cs.SD
We propose a preference optimization framework with Large Audio-Language Model (LALM) feedback for controllable non-verbal vocalization (NVV) generation in continuous autoregressive speech models. To construct preference data without human preference annotation, we build a bilingual prompt corpus by combining NVV-injected real transcripts with LLM-generated semantically aligned prompts, perform stochastic model rollouts, and use a LALM to rank candidate utterances and form same-prompt chosen–rejected pairs. We then adopt a two-stage optimization strategy: Rejection Sampling Fine-Tuning (RSFT) first adapts the model to LALM-selected high-scoring samples, followed by Anchored Flow-DPO, which formulates pairwise preference optimization using utterance-level flow-matching loss and retains the chosen-sample flow-matching objective as an SFT anchor. This design enables DPO-style preference learning without explicit sequence likelihoods while preserving direct supervision on preferred realizations. On the official 1,600-utterance NVVSpeech Challenge Track~2 test set, our method achieves a Final Track2Score of \textbf{75.80} (79.39 ZH / 72.21 EN), outperforming the VoxCPM2 baseline by \textbf{+1.84}. The improvements are mainly driven by higher NVV Accuracy and NVV Perceptual Effect, while Overall Quality remains stable.
40. The Second MLC-SLM Challenge: Multilingual Conversational Speech Diarization, Recognition, and Understanding
Authors: Bingshen Mu, Mingchen Shao, Zhennan Lin, Liumeng Xue, Hexin Liu et al.
Categories: eess.AS, cs.SD
This paper summarizes the Interspeech2026 second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge, which aims to advance the development of effective multilingual conversational speech language models. We describe the two challenge tasks: multilingual conversational speech diarization and recognition, and multilingual conversational speech understanding, together with the released real-world conversational speech dataset, evaluation protocols, and baseline systems. The challenge attracted 91 teams worldwide, with 704 valid leaderboard results and 14 technical reports across the two tasks. Based on the participating systems, we summarize representative approaches and distill practical insights into multilingual conversational speech recognition and understanding to support future research in the community.
41. A Native-Reference Coordinate Geometry for L2 Pronunciation Deviation Using Self-Supervised Speech Models
Authors: Tina Raissi, Nhan Phan, Mikko Kurimo
Categories: cs.CL
Self-supervised speech models encode rich phonetic information, but it remains unclear how to transform this information into interpretable metrics for second-language (L2) pronunciation assessment in spontaneous speech. We propose a native-reference coordinate geometry in which phone-class averages from native speech define a low-dimensional reference subspace, and L2 speech is evaluated by its distance to matching native phone-class coordinates. Unlike prior distance-based approaches, our method does not require parallel recordings with matched linguistic content or dedicated pronunciation labels. Across different self-supervised encoders and modeling choices, the resulting native-reference distances show negative Spearman correlations up to -0.5 with speaking proficiency, indicating that higher-proficiency speakers tend to lie closer to the native-reference space.
42. An Explainable DistilBERT-BiLSTM-Attention Framework for Binary and Multi-Class Hate Speech Detection
Authors: Rameesha Zia, Muhammad Shahid Iqbal Malik
Categories: cs.CL, cs.AI
Hate speech on social media poses serious risks to social harmony, mental well-being, and public safety, making its timely and accurate detection essential for content moderation systems. Most existing studies focus on binary classification, evaluated their frameworks on a single dataset, and provide limited insight into how decisions are made, which limits their real-world applicability. In addition, limited work is done on the explainability of their predictive inference. To address these challenges, this study proposes a multilevel and explainable hate speech detection framework. The proposed model integrates DistilBERT (Distilled Bidirectional Encoder Representations from Transformers) embeddings with a Bi-LSTM (Bidirectional Long Short-Term Memory) model, and an attention mechanism to capture both contextual meaning and sequential dependencies in text. To enhance trust and transparency, LIME (Local Interpretable Model-agnostic Explanations) is employed to explain model predictions by highlighting influential textual features. The framework is evaluated on two benchmark datasets using both binary and multi-class classification to examine robustness and generalization. In addition, an ablation study is presented to highlight the significance of various components of proposed framework. For binary classification, the proposed model achieves F1-scores of 96.78% on the Davidson dataset and 99.53% on the SMHS dataset. In the multi-class setting, it attains F1-scores of 97.00% and 94.99% on the Davidson and SMHS datasets, respectively, outperforming existing baseline approaches. The results demonstrate that multilevel evaluation improves the reliability that the proposed framework effectively balances performance and efficiency. This makes the framework suitable for practical hate speech moderation systems that require accurate, generalizable, and explainable decisions.
43. Ruby-ASR: Evidence-Preserving Supervision for Joint Orthographic and Lexical-Reading Recognition
Authors: Hao Shi, Yun Liu, Xuehao Yang, Jun Liu, Chuanbo Hua et al.
Categories: cs.CL, cs.AI
Conventional Japanese automatic speech recognition (ASR) is supervised by an orthographic transcript, although the same written form can correspond to different lexical readings realized in speech. Such utterances receive an identical target, so their reading distinction is absent from the supervision interface and cannot be recovered reliably by post-hoc text-only grapheme-to-phoneme conversion. We present Ruby-ASR, which refines the conventional target into a span-bound orthographic–lexical-reading sequence. Unlike separate full-sentence orthographic and phonological outputs, the ruby representation locally binds each written span to its realized reading and permits deterministic recovery of both views. We instantiate the target under subtitle-style and verbatim-style transcription conventions using a Qwen3-ASR backbone; a mora-level CTC objective provides auxiliary monotonic reading supervision. The experimental results across five Japanese benchmarks show that refining the recognition target can improve lexical-reading recovery without sacrificing readable orthographic transcription. We release the checkpoints and inference code.
44. SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
Authors: Haobo Zheng, Tan Tang, Yan Chen, Weijie Wang, Yingcai Wu
Categories: cs.CL, cs.AI, cs.IR, cs.LG
Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what information is shared by the group, and how states change over time. Recent studies on multi-party dialogue benchmarks show that existing general-purpose LLM memory systems tend to lose person and group relations or struggle to integrate clues distributed across members, groups, and time. Together, these issues reveal two core bottlenecks: message attribution and relational understanding in multi-party dialogue, and state reconstruction from interleaved histories. To address both, we propose $\textbf{SpeakerMem-R1}$: its dual-track memory stores speaker-labeled verbatim messages and derived states organized into person-level and group-level views, then combines evidence from both tracks by entity, event, and time at query time. To reduce attribution and update errors during structured memory construction while enabling local deployment, we train Writer-R1 with SpeakerLevenshtein and speaker-conditioned GRPO. On GroupMemBench, SocialMemBench, and EverMemBench, SpeakerMem-R1 achieves binary accuracies of 47.9%, 69.2%, and 61.9%, respectively. On the publicly reported EverMemBench leaderboard from EverMind-AI, we achieves 62.33%, the best reported result among the latest state-of-the-art frameworks. It also achieves 70.85% on all 1,986 LoCoMo questions, which we use as a two-person long-term conversation boundary test. In a controlled evaluation of 305 questions, RL raises the SFT Writer’s mean accuracy from 57.38% to 68.20%. We report both binary accuracy and token-F1, and ablations show that the verbatim and structured tracks, as well as person-level and group-level views, are complementary under the standardized evaluation interface.
45. Monitoring Urban Traffic Dynamics at Fine Spatiotemporal Resolution Using Distributed Acoustic Sensing and Deep Learning
Authors: Hao Tian, Heng Cai, Xiaowei Chen, Yifan Yang
Categories: cs.LG
Mapping the distribution of traffic dynamics at high spatiotemporal resolution is a fundamental question in transportation research. Distributed acoustic sensing (DAS), an innovative seismic observation tool, emerges as a promising solution for real-time urban traffic monitoring at high spatial and temporal scales. Distributed acoustic sensing repurposes existing underground fiber-optic cables as dense, continuous sensor arrays, enabling passive and privacy-preserving monitoring of roadway traffic activity at meter-level spatial and second-level temporal resolution. This study examines whether integrating DAS and deep learning models can serve as a continuous and efficient urban traffic observatory for revealing urban traffic dynamics (i.e. traffic volume and congestion, event-driven changes) at high spatiotemporal resolution. Using a DAS deployment along a roadway network in the City of College Station, Texas, USA, this study develops a deep learning-empowered analytical framework that converts raw ground vibration waveforms into spatiotemporal representations, detects vehicle trajectory, and infers traffic states from aggregated traffic volume and speed. A hybrid training strategy combining synthetic and manually annotated DAS images is used to improve vehicle detection under noisy and congested conditions, with model outputs further aggregated to characterize system-level traffic dynamics.
46. Sound State Encodings in Translational Separation Logic Verifiers (Extended Version)
Authors: Hongyi Ling, Thibault Dardinier, Ellen Arlt, Peter Müller
Categories: cs.PL
Automated program verifiers are often organized into a front-end, which encodes an input program into an intermediate verification language (IVL), and a back-end, which proves that the IVL program is correct. Soundness of such translational verifiers requires that the back-end verification is sound and that correctness of the IVL program implies correctness of the input program. Existing formalizations for translational verifiers based on separation logic target the former, but support the latter only under the strong assumption that there exists a separation logic for the input program with the same state model as the IVL. This assumption is unrealistic in practice, especially since the state model also defines the supported separation logic resources. We present the first formal framework for proving the soundness of translational separation logic verifiers with non-trivial state encodings. To be applicable to various front-ends and IVLs, our framework only assumes the existence of a homomorphic encoding relation between the front-end and IVL state models. At the core of our framework is a novel condition, backward satisfiability, which is crucial to guarantee the soundness of the front-end translation. We formalize our framework for front-end verifiers based on concurrent separation logic and separation logic IVLs, such as Raven, VeriFast, and Viper. We demonstrate its expressiveness by proving soundness for three common state encodings. Our framework and all proofs are formalized in Isabelle/HOL.
47. Multimodal Voice Activity Projection for Social Robot Mediation: Expected Behavior and Deployment Constraints
Authors: Antonio Cano, Guillermo Perez, Luis Merino, Randy Gomez
Categories: cs.RO
Turn-taking prediction is especially relevant for social robots that act as mediators in human-human interaction, where the expected action is often not to speak, but to orient, wait, avoid interruption, or prepare a balanced intervention. This paper presents Multimodal Voice Activity Projection (MM-VAP) as a human state-aware perception layer for future robot mediation behavior. The model estimates the future evolution of the conversational floor from synchronized audio-visual evidence and derives turn-taking events such as Hold, Shift, Shift prediction, Backchannel prediction, and overlap-related states. The approach uses VA-related pretrained audio-visual encoders, LoRA adaptation, inter-speaker attention, and zero-shot event inference from future voice activity projections. Experiments on NoXi, NoXi+J, and Haru EDR support the feasibility of this formulation, especially for floor management events that can be connected to gaze preparation, active listening, and conservative intervention. Finally, the paper defines the expected robot output interface and discusses the main deployment constraints, including real-time inference, preprocessing latency, multimodal synchronization, and input-quality monitoring.