每日 arXiv

音频 · 语音 · 音乐 · 声学

每日新爬取的 arXiv 论文，按评分排序。中文摘要帮你快速判断是否值得深读。

2026-10-08
日期2026-10-08
已评分—
均分—
最高—

Daily Papers — 2026-10-08

3 papers on audio, speech, music, and acoustics.

1. MiDashengLM-Spatial: Unifying General Audio Understanding and Spatial Awareness

Authors: Jinbo Hu, Hang Su, Lichun Fan, Heinrich Dinkel, Gang Li et al.

Categories: cs.SD, eess.AS Score: 5.89/10 (Obj:7 Id:4 Ind:6 Comp:6 Eff:7 Nov:5 Rep:7)

  • Strength: 在 STAR-Bench SR 上把 channel-swap 全对率从单声道模型的 $\le 16.9$ 拉到 $72.6$，证明预测确实依赖双耳线索，同时 18 项单声道 benchmark 有 12 项不低于底座。
  • Weakness: 没有和 SPUR、Spatial-Omni 等同范式空间 LALM 对比，也缺「去掉 HSSC」消融，核心组件的必要性和「首个统一模型」的定位都缺证据。
  • Full review: Claude Code 全文七公理审稿

Large audio-language models (LALMs) have achieved strong performance in general audio understanding, yet most are designed for monaural input and discard the inter-channel cues essential for spatial perception. In contrast, existing spatial audio-language models are purpose-built for spatial tasks and fail to capitalize on the general understanding capabilities of monaural LALMs. We present MiDashengLM-Spatial, the first open-source end-to-end unified audio-language model, to our knowledge, which supports both general audio understanding and spatial awareness within a single architecture. It extends MiDashengLM with a spatial audio encoder, Spatial-Dasheng, integrated through a hierarchical semantic-to-spatial conditioning module that injects intermediate semantic representations into the spatial branch at multiple depths while preserving the original semantic pathway. To provide spatial audio-language supervision at scale, we develop a data synthesis pipeline that renders diverse spatial acoustic scenes with scene-level spatial descriptions and question-answer pairs. Experiments show that Spatial-Dasheng achieves strong performance on sound event localization and detection in real-world scenes, and that MiDashengLM-Spatial substantially outperforms existing LALMs on spatial understanding and reasoning benchmarks. Meanwhile, it remains competitive with state-of-the-art 8B-scale LALMs on diverse monaural benchmarks, demonstrating that spatial awareness can be acquired without compromising general audio understanding. The source code and model checkpoint are available at https://github.com/xiaomi-research/midashenglm-spatial and https://huggingface.co/mispeech/midashenglm-spatial.

2. Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech

Authors: Shiao Zhu, Lianbo Liu, Sizhen Lyu, Yuzhe Wang, Sheng Li et al.

Categories: cs.SD, cs.CL, eess.AS Score: 5.16/10 (Obj:7 Id:4 Ind:5 Comp:7 Eff:5 Nov:5 Rep:4)

  • Strength: 诊断实验（Table 1、Fig. 1）清楚地说明了描述对齐只是弱代理（ParaCLAP T2S 与声学指标的相关仅 .008–.029），SRSP 在 Table 2 五个声学指标、两个分区全部第一，40 组比较中 38 组显著。
  • Weakness: 标题声称超越 caption 监督，却没有比 caption-SFT 规划器和同奖励 RFT 基线，主观结论只靠单个 Gemini 判官、没有人工听测。
  • Full review: Claude Code 全文七公理审稿

Natural-language style descriptions provide an interpretable interface between large language models (LLMs) and controllable text-to-speech (TTS). However, using descriptions as pseudo-labels compresses target acoustics into text, and descriptive fidelity need not imply effective control of a particular synthesizer. We empirically show that speech-text alignment only weakly predicts downstream acoustic similarity among candidate instructions for the same utterance. We therefore propose Speech-Rewarded Style Planning (SRSP), which trains a text-based style planner through a frozen downstream TTS model. Given dialogue history and response text, the planner generates candidate instructions and is optimized with group-relative policy optimization (GRPO), using the teacher-forced likelihood of target speech tokens as the reward. On an English subset of the ISCSLP 2026 CoT-TTS corpus, SRSP achieves higher speech-style and emotion similarity to target speech and lower mel-cepstral distortion than the Base LLM and target-audio-informed captioning baselines. LLM-based expressive speech evaluation further shows gains over all baselines in contextual appropriateness and reference consistency.

3. Edit Who Speaks, Control How They Speak: Global Timbre Editing and Local Instruction Control for TTS

Authors: Junchuan Zhao, Chenglin Xu, Wei Zeng, Haoyang Li, Yiwen Guo et al.

Categories: cs.SD, eess.AS Score: 5.16/10 (Obj:7 Id:4 Ind:5 Comp:6 Eff:6 Nov:5 Rep:3)

  • Strength: 段边界 KV 重算免训练，在 Qwen3-TTS-VD 上把 SegAcc 从 TED-TTS 的 $74.25$ 提到 $82.30$，消融显示比复用旧 KV 的截短 cache 高 $24$ 点。
  • Weakness: 音色编辑的训练数据、评测目标和基线同出自 Qwen3-TTS-VD，入表基线都不是编辑器，未比开源的 Step-Audio-EditX 和机制最近的 Kang et al. KV-cache swapping。
  • Full review: Claude Code 全文七公理审稿

Instruction-based text-to-speech (TTS) offers control over voice characteristics and speech expression through interfaces including voice cloning and text-based voice design. Voice cloning reproduces a reference voice, whereas text-based voice design creates a voice from a natural-language description. However, neither interface directly enables users to modify the timbre of a given reference and synthesize speech with the modified voice. Meanwhile, utterance-level expressive instructions leave changes across individual text segments underspecified. We introduce \textbf{EDICT}, a framework that unifies global timbre editing and local expressive control by using an edited acoustic reference to anchor voice identity across segments. To enable synthesis with an instruction-edited voice, EDICT combines reference audio with structured timbre edits to generate an edited reference in codec-token space. This representation serves as a shared voice anchor for a frozen TTS backbone, allowing segment-specific natural-language instructions to guide expression. To accommodate instruction changes while supporting acoustic continuity, EDICT rebuilds the KV cache at each segment boundary, refreshing instruction conditioning while retaining bounded acoustic context from previously generated speech. Evaluations on our proposed TimbreEdit-Bench and IntraTTS-Bench demonstrate improved timbre editing and a favorable balance between local instruction adherence, speaker consistency, and transition quality. Audio demos are available.