https://nanless.github.io/audio-paper-digest-blog/tags/%E6%A8%A1%E5%9E%8B%E8%AF%84%E4%BC%B0/ Recent content in 模型评估 on 语音/音频论文速递 Hugo zh-cn Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-bayesian-approach-to-singing-skill-evaluation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-bayesian-approach-to-singing-skill-evaluation/ 音乐理解 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-dataset-of-robot-patient-and-doctor-patient/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-dataset-of-robot-patient-and-doctor-patient/ 语音对话系统 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-superb-style-benchmark-of-self-supervised/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-superb-style-benchmark-of-self-supervised/ 音频深度伪造检测 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-text-to-text-alignment-algorithm-for-better/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-a-text-to-text-alignment-algorithm-for-better/ 模型评估 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-acoustic-non-stationarity-objective-assessment/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-acoustic-non-stationarity-objective-assessment/ 音频分类 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-adaptive-spectral-weighting-in-sagittal-plane/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-adaptive-spectral-weighting-in-sagittal-plane/ 声源定位 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-aligning-generative-speech-enhancement-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-aligning-generative-speech-enhancement-with/ 语音增强 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ard-a-framework-for-retrieving-and-describing/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ard-a-framework-for-retrieving-and-describing/ 音频大模型 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-assessing-identity-leakage-in-talking-face/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-assessing-identity-leakage-in-talking-face/ 说话人脸生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attention-based-encoder-decoder-target-speaker/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attention-based-encoder-decoder-target-speaker/ 说话人分离 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attentive-av-fusionnet-audio-visual-quality/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attentive-av-fusionnet-audio-visual-quality/ 音视频 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-auditory-illusion-benchmark-for-large-audio/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-auditory-illusion-benchmark-for-large-audio/ 模型评估 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-automatic-estimation-of-speaker-diarization-error/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-automatic-estimation-of-speaker-diarization-error/ 说话人分离 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-avo-65-a-large-scale-hierarchical-audio-visual/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-avo-65-a-large-scale-hierarchical-audio-visual/ 音视频 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-benchmarking-humans-and-machines-on-complex/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-benchmarking-humans-and-machines-on-complex/ 音频问答 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-benchmarking-music-autotagging-with-mgphot-expert/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-benchmarking-music-autotagging-with-mgphot-expert/ 音乐信息检索 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-break-the-beat-controllable-midi-to-drum-audio/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-break-the-beat-controllable-midi-to-drum-audio/ 音乐生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-bridgecode-a-dual-speech-representation-paradigm/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-bridgecode-a-dual-speech-representation-paradigm/ 语音合成 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-bsmp-senetband-split-magnitude-phase-network-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-bsmp-senetband-split-magnitude-phase-network-for/ 语音增强 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-can-hierarchical-cross-modal-fusion-predict-human/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-can-hierarchical-cross-modal-fusion-predict-human/ 模型评估 | 6.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-clawmark-a-living-world-benchmark-for-multi-turn/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-clawmark-a-living-world-benchmark-for-multi-turn/ 基准测试 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-combining-multi-order-attention-and-multi/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-combining-multi-order-attention-and-multi/ 语音合成 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-content-leakage-in-librispeech-and-its-impact-on/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-content-leakage-in-librispeech-and-its-impact-on/ 语音匿名化 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cutscene-agent-an-llm-agent-framework-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cutscene-agent-an-llm-agent-framework-for/ 生成模型 | 8.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-dissr-disentangling-speech-representation-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-dissr-disentangling-speech-representation-for/ 语音增强 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-do-bias-benchmarks-generalise-evidence-from-voice/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-do-bias-benchmarks-generalise-evidence-from-voice/ 模型评估 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-do-speech-llms-learn-crossmodal-embedding-spaces/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-do-speech-llms-learn-crossmodal-embedding-spaces/ 音频检索 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-do-you-hear-what-i-mean-quantifying-the/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-do-you-hear-what-i-mean-quantifying-the/ 语音合成 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-dsrms-transunet-a-decentralized-non-shifted/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-dsrms-transunet-a-decentralized-non-shifted/ 声源定位 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-efficient-audio-visual-inference-via-token/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-efficient-audio-visual-inference-via-token/ 音频问答 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-speech-intelligibility-prediction-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-speech-intelligibility-prediction-for/ 语音增强 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-bias-in-spoken-dialogue-llms-for-real/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-bias-in-spoken-dialogue-llms-for-real/ 模型评估 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-compositional-structure-in-audio/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-compositional-structure-in-audio/ 模型评估 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-disentangled-representations-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-disentangled-representations-for/ 音乐生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-emotion-recognition-in-spoken-language/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-emotion-recognition-in-spoken-language/ 语音情感识别 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-high-resolution-piano-sustain-pedal/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-high-resolution-piano-sustain-pedal/ 音乐信息检索 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-pretrained-speech-embedding-systems/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-evaluating-pretrained-speech-embedding-systems/ 语音生物标志物 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-exploring-how-audio-effects-alter-emotion-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-exploring-how-audio-effects-alter-emotion-with/ 音乐理解 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fine-grained-frame-modeling-in-multi-head-self/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fine-grained-frame-modeling-in-multi-head-self/ 语音伪造检测 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fusemos-perceptual-evaluation-of-text-to-music/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fusemos-perceptual-evaluation-of-text-to-music/ 音乐生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-game-time-evaluating-temporal-dynamics-in-spoken/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-game-time-evaluating-temporal-dynamics-in-spoken/ 语音对话系统 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-hashing-baseline-rethinking-hashing-in-the-age-of/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-hashing-baseline-rethinking-hashing-in-the-age-of/ 音频检索 音频分类 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-hd-ppt-hierarchical-decoding-of-content-and/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-hd-ppt-hierarchical-decoding-of-content-and/ 语音合成 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-how-to-label-resynthesized-audio-the-dual-role-of/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-how-to-label-resynthesized-audio-the-dual-role-of/ 音频深度伪造检测 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/icassp2026-task-033/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/icassp2026-task-033/ 共 16 篇 ICASSP 2026 模型评估 方向论文 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-identifying-the-minimal-and-maximal-phonetic/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-identifying-the-minimal-and-maximal-phonetic/ 语音识别 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-identity-leakage-through-accent-cues-in-voice/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-identity-leakage-through-accent-cues-in-voice/ 语音匿名化 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-improving-the-speaker-anonymization-evaluations/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-improving-the-speaker-anonymization-evaluations/ 语音匿名化 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-integrating-speaker-embeddings-and-llm-derived/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-integrating-speaker-embeddings-and-llm-derived/ 说话人分离 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-interpretable-music-harmonic-analysis-through/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-interpretable-music-harmonic-analysis-through/ 音乐理解 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-investigating-modality-contribution-in-audio-llms/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-investigating-modality-contribution-in-audio-llms/ 模型评估 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-investigating-the-effect-of-sentence-level/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-investigating-the-effect-of-sentence-level/ 语音识别 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-learning-linearity-in-audio-consistency/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-learning-linearity-in-audio-consistency/ 音频生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-large-speech-language-models-as/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-large-speech-language-models-as/ 语音情感识别 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-multiple-speech-enhancers-for-non/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-multiple-speech-enhancers-for-non/ 模型评估 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-prediction-entropy-for-automatic/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-prediction-entropy-for-automatic/ 音频分类 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-lingometer-on-device-personal-speech-word/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-lingometer-on-device-personal-speech-word/ 语音活动检测 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-llac-learned-lossless-audio-codec/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-llac-learned-lossless-audio-codec/ 音频无损编码 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-measuring-prosody-diversity-in-zero-shot-tts-a/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-measuring-prosody-diversity-in-zero-shot-tts-a/ 语音合成 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mitigating-language-prior-induced-hallucinations/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mitigating-language-prior-induced-hallucinations/ 多模态模型 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mix2morph-learning-sound-morphing-from-noisy-mixes/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mix2morph-learning-sound-morphing-from-noisy-mixes/ 音频生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mixture-of-experts-based-soft-label-learning-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mixture-of-experts-based-soft-label-learning-for/ 语音情感识别 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mmeb-v3-measuring-the-performance-gaps-of-omni/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mmeb-v3-measuring-the-performance-gaps-of-omni/ 基准测试 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mr-flowdpo-multi-reward-direct-preference/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mr-flowdpo-multi-reward-direct-preference/ 音乐生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-multi-layer-attentive-probing-improves-transfer/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-multi-layer-attentive-probing-improves-transfer/ 生物声学 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-nemotron-3-nano-omni-efficient-and-open/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-nemotron-3-nano-omni-efficient-and-open/ 多模态模型 | 8.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-optimizing-speech-language-models-for-acoustic/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-optimizing-speech-language-models-for-acoustic/ 语音合成 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-perceptual-quality-assessment-for-stylized/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-perceptual-quality-assessment-for-stylized/ 模型评估 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-pianoroll-event-a-novel-score-representation-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-pianoroll-event-a-novel-score-representation-for/ 音乐生成 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-probing-whisper-for-dysarthric-speech-in/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-probing-whisper-for-dysarthric-speech-in/ 语音生物标志物 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-psp-an-interpretable-per-dimension-accent/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-psp-an-interpretable-per-dimension-accent/ 基准测试 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-qastanet-a-dnn-based-quality-metric-for-spatial/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-qastanet-a-dnn-based-quality-metric-for-spatial/ 空间音频 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ras-a-reliability-oriented-metric-for-automatic/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ras-a-reliability-oriented-metric-for-automatic/ 语音识别 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-reference-aware-sfm-layers-for-intrusive/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-reference-aware-sfm-layers-for-intrusive/ 语音评估 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-reliable-ai-via-age-balanced-validation-fair/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-reliable-ai-via-age-balanced-validation-fair/ 语音生物标志物 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-rho-perfect-correlation-ceiling-for-subjective/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-rho-perfect-correlation-ceiling-for-subjective/ 模型评估 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-scalable-evaluation-for-audio-identification-via/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-scalable-evaluation-for-audio-identification-via/ 音频检索 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-segmentwise-pruning-in-audio-language-models/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-segmentwise-pruning-in-audio-language-models/ 音频问答 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sfm-tts-lightweight-and-rapid-speech-synthesis/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sfm-tts-lightweight-and-rapid-speech-synthesis/ 语音合成 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sing-what-you-fit-a-perception-based-dataset-and/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sing-what-you-fit-a-perception-based-dataset-and/ 音乐信息检索 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-singmos-pro-an-comprehensive-benchmark-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-singmos-pro-an-comprehensive-benchmark-for/ 歌唱语音合成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sp-mcqa-evaluating-intelligibility-of-tts-beyond/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sp-mcqa-evaluating-intelligibility-of-tts-beyond/ 语音合成 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-spade-structured-pruning-and-adaptive/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-spade-structured-pruning-and-adaptive/ 语音合成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-spam-style-prompt-adherence-metric-for-prompt/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-spam-style-prompt-adherence-metric-for-prompt/ 语音合成 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sparse-autoencoders-make-audio-foundation-models/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sparse-autoencoders-make-audio-foundation-models/ 模型评估 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-speech-quality-based-localization-of-low-quality/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-speech-quality-based-localization-of-low-quality/ 语音质量评估 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-step-audio-r15-technical-report/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-step-audio-r15-technical-report/ 语音对话系统 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-streamingbench-assessing-the-gap-for-mllms-to/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-streamingbench-assessing-the-gap-for-mllms-to/ 基准测试 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-stylebench-evaluating-speech-language-models-on/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-stylebench-evaluating-speech-language-models-on/ 基准测试 | 8.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-switchcodec-adaptive-residual-expert-sparse/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-switchcodec-adaptive-residual-expert-sparse/ 音频生成 | 8.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-symphony-rendering-midi-and-composer-conditioned/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-symphony-rendering-midi-and-composer-conditioned/ 音乐生成 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-synthetic-yet-striking-assessing-vocal-charisma/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-synthetic-yet-striking-assessing-vocal-charisma/ 语音合成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tau-a-benchmark-for-cultural-sound-understanding/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tau-a-benchmark-for-cultural-sound-understanding/ 音频问答 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-test-time-scaling-for-auditory-cognition-in-audio/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-test-time-scaling-for-auditory-cognition-in-audio/ 音频问答 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-the-3rd-clarity-prediction-challenge-a-machine/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-the-3rd-clarity-prediction-challenge-a-machine/ 语音增强 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-the-muse-benchmark-probing-music-perception-and/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-the-muse-benchmark-probing-music-perception-and/ 音乐理解 | 8.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-the-structured-output-benchmark-a-multi-source/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-the-structured-output-benchmark-a-multi-source/ 基准测试 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-evaluating-generative-audio-insights-from/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-evaluating-generative-audio-insights-from/ 模型评估 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-robust-dysarthric-speech-recognition-llm/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-robust-dysarthric-speech-recognition-llm/ 语音识别 | 9.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-triad-tri-head-with-auxiliary-duplicating/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-triad-tri-head-with-auxiliary-duplicating/ 音频事件检测 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tta-transcribe-translate-and-alignment-for-cross/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tta-transcribe-translate-and-alignment-for-cross/ 语音识别 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-universr-unified-and-versatile-audio-super/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-universr-unified-and-versatile-audio-super/ 音频超分辨率 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-unseen-but-not-unknown-using-dataset-concealment/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-unseen-but-not-unknown-using-dataset-concealment/ 语音质量评估 | 8.3/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-utilizing-information-theoretic-approach-to-study/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-utilizing-information-theoretic-approach-to-study/ 生物声学 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-v2a-dpo-omni-preference-optimization-for-video-to/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-v2a-dpo-omni-preference-optimization-for-video-to/ 视频到音频生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-walking-through-uncertainty-an-empirical-study-of/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-walking-through-uncertainty-an-empirical-study-of/ 音频问答 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-wav2lev-predicting-levenshtein-edit-operation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-wav2lev-predicting-levenshtein-edit-operation/ 语音识别 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-when-noise-lowers-the-loss-rethinking-likelihood/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-when-noise-lowers-the-loss-rethinking-likelihood/ 音乐生成 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-when-silence-matters-the-impact-of-irrelevant/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-when-silence-matters-the-impact-of-irrelevant/ 模型评估 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-when-voice-matters-a-controlled-study-of-audio/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-when-voice-matters-a-controlled-study-of-audio/ 模型评估 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-why-do-speech-language-models-fail-to-generate/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-why-do-speech-language-models-fail-to-generate/ 语音生成 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-z-scores-a-metric-for-linguistically-assessing/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-z-scores-a-metric-for-linguistically-assessing/ 模型评估 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-all-that-glitters-is-not-audio-rethinking-text/ Tue, 28 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-all-that-glitters-is-not-audio-rethinking-text/ 音频问答 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-comparison-of-semg-encoding-accuracy-across/ Tue, 28 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-comparison-of-semg-encoding-accuracy-across/ 语音生物标志物 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-explainable-ai-in-speaker-recognition-making/ Tue, 28 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-explainable-ai-in-speaker-recognition-making/ 说话人识别 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-27-audio-video-verbal-analysis-avva-for-capturing/ Mon, 27 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-27-audio-video-verbal-analysis-avva-for-capturing/ 音频问答 | 6.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-27-identifying-and-typifying-demographic-unfairness/ Mon, 27 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-27-identifying-and-typifying-demographic-unfairness/ 语音识别 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-27-transformer-based-rhythm-quantization-of/ Mon, 27 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-27-transformer-based-rhythm-quantization-of/ 音乐信息检索 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-this-wasnt-made-for-me-recentering-user/ Fri, 24 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-this-wasnt-made-for-me-recentering-user/ 语音识别 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-audita-a-new-dataset-to-audit-humans-vs-ai-skill/ Fri, 24 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-audita-a-new-dataset-to-audit-humans-vs-ai-skill/ 音频问答 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-evaluation-of-automatic-speech-recognition-using/ Fri, 24 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-evaluation-of-automatic-speech-recognition-using/ 语音识别 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-preferences-of-a-voice-first-nation-large-scale/ Fri, 24 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-preferences-of-a-voice-first-nation-large-scale/ 语音合成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-time-vs-layer-locating-predictive-cues-for/ Fri, 24 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-time-vs-layer-locating-predictive-cues-for/ 语音生物标志物 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-aligning-stuttered-speech-research-with-end-user/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-aligning-stuttered-speech-research-with-end-user/ 1. **问题**：当前口吃语音技术研究与口吃者（PWS）及言语语言病理学家（SLP）的实际需求存在系统性脱节，研究重点、任务定义和评估方法未能充分以用户为中心。 2. **方法核心**：通过两部分结合分析：1）对228篇相关论文进行范围综述，提出研究任务分类法并分析研究现状；2）对70名利益相 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-centering-ecological-goals-in-automated/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-centering-ecological-goals-in-automated/ 这篇论文旨在解决一个关键问题：为什么近年来在动物个体自动识别（基于图像或声音）上报告的高准确率算法，却很少转化为生态学实践中的常规工具？其方法核心是提出一个“以生态目标为中心”的评估与部署框架，强调自动化识别的有用性取决于其服务的具体生态问题、可用数据以及错误类型带来的实际后果。与以往主要关注算法准 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-embedding-based-intrusive-evaluation-metrics-for/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-embedding-based-intrusive-evaluation-metrics-for/ 1. **问题**：音乐源分离（MSS）领域常用的客观评估指标（BSS-Eval）与人类感知评分相关性较低，导致模型评估不够准确。 2. **方法核心**：提出两种基于嵌入的侵入式评估指标：在预训练MERT模型的嵌入空间上计算目标与分离信号的均方误差（MSE_MERT）和一种逐曲目的Fréchet音 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-flip-towards-understanding-and-interpreting/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-flip-towards-understanding-and-interpreting/ 这篇论文旨在解决对多语言、多模态句子嵌入（如SONAR, LaBSE）的可解释性问题。核心方法是提出一种称为因子化线性投影（FLiP）的模型，通过将嵌入向量线性投影到词汇表空间来提取关键词，以此作为理解嵌入内容的代理任务。与之前非因子化的线性探测方法（如LiP）和SpLiCE相比，FLiP在关键词提 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-onote-benchmarking-omnimodal-notation-processing/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-onote-benchmarking-omnimodal-notation-processing/ 1. **问题**：当前多模态大模型在音乐符号处理（Omnimodal Notation Processing, ONP）领域存在严重缺陷：研究碎片化、模型存在严重的符号偏差（偏向五线谱）、且普遍依赖不可靠的“LLM-as-a-Judge”评估方法，掩盖了模型在音乐理论推理上的系统性失败。 2. https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-reducing-the-offline-streaming-gap-for-unified/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-reducing-the-offline-streaming-gap-for-unified/ 1. **问题**：训练一个既能高精度离线转录又能低延迟流式识别的统一ASR模型极具挑战性，传统方法在低延迟下性能会急剧下降。 2. **方法核心**：提出一个统一的Transducer框架，结合分块注意力（含右上下文）和动态块卷积（DCConv）来适配两种模式。核心创新是引入了模式一致性正则化损失 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-speechparaling-bench-a-comprehensive-benchmark/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-speechparaling-bench-a-comprehensive-benchmark/ 1. **问题**：现有大型音频语言模型在副语言（如情绪、语气、音色）生成与理解能力上的评估存在特征覆盖不全、评估方法主观且不可扩展的问题。 2. **方法**：提出了SpeechParaling-Bench，一个包含1000余个中英平行语音查询、覆盖超过100个细粒度副语言特征的综合基准。基准 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-utterance-level-methods-for-identifying-reliable/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-utterance-level-methods-for-identifying-reliable/ 1. **要解决什么问题**：儿童语音自动识别（ASR）错误率高，影响语言学习、阅读辅助等应用。传统置信度估计方法在噪声大、模式多变的儿童语音上可能失效。需要一种在转录后（utterance级别）自动识别哪些ASR输出是可靠的方法，以减少人工审核负担。 2. **方法核心是什么**：提出两种基于 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-detecting-hallucinations-in-speechllms-at/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-detecting-hallucinations-in-speechllms-at/ 本文旨在解决语音大模型（SpeechLLMs）在推理时产生的“幻觉”问题，即生成与输入音频不符的流畅文本。现有方法依赖昂贵的黄金标准输出，而文本LLM的方法无法捕捉音频特有信号。为此，作者提出了四个基于注意力图的轻量级指标（AudioRatio, AudioConsistency, AudioEnt https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-halluaudio-a-comprehensive-benchmark-for/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-halluaudio-a-comprehensive-benchmark-for/ 这篇论文旨在解决大型音频语言模型（LALM）中普遍存在的“幻觉”问题（即生成与音频证据不符的内容）缺乏系统性评估工具的难题。为此，作者构建并发布了**HalluAudio**，这是首个大规模、多领域（语音、环境声、音乐）、多任务（二分类、多选、属性验证、开放生成）的人工验证音频幻觉检测基准，包含超过 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-mtr-duplexbench-towards-a-comprehensive/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-mtr-duplexbench-towards-a-comprehensive/ 这篇论文旨在解决当前全双工语音语言模型（FD-SLMs）评测体系的一个关键缺陷：缺乏对多轮、连续对话能力的系统性评估。现有基准多关注单轮交互或特定对话特性（如打断），忽略了模型在多轮语境下维持指令遵循、安全等核心能力的一致性。为此，作者提出了**MTR-DuplexBench**，一个全新的多轮全双 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-voice-of-india-a-large-scale-benchmark-for-real/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-voice-of-india-a-large-scale-benchmark-for-real/ 这篇论文旨在解决现有印度语言语音识别（Indic ASR）基准不反映真实场景、评估方法不公平的核心问题。为此，作者构建了“Voice of India”大规模基准，其数据源自3.6万名说话者的非脚本化电话对话，覆盖15种主要印度语言和139个地区集群，总计536小时。关键创新在于采用了考虑拼写变体的 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-a-state-space-representation-of-the-boundary/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-a-state-space-representation-of-the-boundary/ 本文旨在解决传统房间声学建模中多种方法（如边界元法、延迟网络、几何声学）彼此独立、缺乏统一理论基础的问题。作者提出了一种名为**边界积分算子状态空间（BIOSS）** 的新框架。该框架的核心是将描述声场的边界积分方程重新表述为一个状态空间模型，其中**状态是房间边界上的声压分布函数**，系统动态由* https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-anonymization-not-elimination-utility-preserved/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-anonymization-not-elimination-utility-preserved/ 这篇论文针对语音数据隐私保护中“隐私泄露”与“数据效用损失”的核心矛盾，提出了一个新颖的两阶段框架。首先，为解决语音匿名化（保护“谁在说”）中身份多样性不足和可控性差的问题，提出了基于流匹配的说话人嵌入匿名器（F3-VA），它能生成多样且与原始说话人充分分离的新身份。其次，为解决内容匿名化（保护“说 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-benign-fine-tuning-breaks-safety-alignment-in/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-benign-fine-tuning-breaks-safety-alignment-in/ 这篇论文首次系统研究了**良性音频数据微调对音频大模型安全对齐的破坏性影响**。核心问题是：用户出于提升性能的目的，在完全无害的音频数据上微调模型，是否会意外削弱其拒绝有害指令的能力？作者提出了一个**基于嵌入空间邻近性的过滤框架**，通过计算良性音频与有害音频在模型内部或外部参考编码器空间中的距离 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-claricodec-optimising-neural-speech-codes-for/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-claricodec-optimising-neural-speech-codes-for/ 本文针对卫星、水下通信等超低比特率（200bps）场景下，传统神经语音编解码器因优化重建质量而牺牲可懂度的问题，提出了ClariCodec。其核心方法是将编码器的量化过程重新定义为一个随机策略，并利用强化学习（RL），以词错率（WER）作为奖励信号对编码器进行微调，而冻结解码器等声学重建管线。实验表 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-coexisting-tempo-traditions-in-beethovens-piano/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-coexisting-tempo-traditions-in-beethovens-piano/ 本文旨在挑战音乐表演实证研究中普遍使用的单一回归分析模型，该模型常将历史速度变化描绘为一个单向、统一的过程。作者提出，这种模型掩盖了多种演奏传统并存的事实。研究通过对贝多芬五首钢琴与大提琴奏鸣曲（Op. 5, 69, 102）在1930-2012年间超过一百个乐章录音的逐小节速度数据进行K-mean https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-flip-towards-understanding-and-interpreting/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-flip-towards-understanding-and-interpreting/ 本文提出**FLiP**，一种**因子化线性投影模型**，旨在**理解并解释**多语言、多模态句子嵌入空间（如SONAR, LaBSE, Gemini）。核心思想是将嵌入空间的解释转化为一个**线性关键词提取任务**：通过一个简单的线性投影，从句子嵌入向量中恢复出构成该句子的词汇。实验表明，训练良好 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-from-reactive-to-proactive-assessing-the/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-from-reactive-to-proactive-assessing-the/ 本文旨在解决现有语音代理评估基准主要关注被动响应，而忽略其主动感知与干预能力的问题。作者提出了**ProVoice-Bench**，这是首个专门用于评估主动式语音代理的基准测试框架。该框架通过一个包含数字状态构建、场景合成、对话生成、声学模拟和对话组装的多阶段数据合成管道，构建了包含1182个高质量 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-hard-to-be-heard-phoneme-level-asr-analysis-of/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-hard-to-be-heard-phoneme-level-asr-analysis-of/ 这篇论文针对两种音系极其复杂、资源极度匮乏的濒危东高加索语言（Archi和Rutul），首次建立了语音识别（ASR）基准。作者们整合并标准化了现有的语言学记录，创建了约50分钟和1小时20分钟的语音-文本数据集。他们评估了多种前沿ASR模型（wav2vec2, Whisper, Qwen2-Audi https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-incremental-learning-for-audio-classification/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-incremental-learning-for-audio-classification/ 本文针对音频分类中的增量学习（持续学习）问题，提出了一种受生物启发的解决方案。核心是解决深度学习模型在学习新任务时对旧知识的“灾难性遗忘”。作者首次将**Hebbian学习**（一种基于神经元同步激活的无监督、无反馈学习规则）与**增量学习**相结合，并设计了一个**核塑性**机制。该机制通过分析训 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-mint-bench-a-comprehensive-multilingual-benchmark/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-mint-bench-a-comprehensive-multilingual-benchmark/ 这篇论文旨在解决指令跟随文本转语音（TTS）领域缺乏系统化评估工具的问题。当前评估存在覆盖不全、诊断粒度粗、多语言支持弱等缺陷。为此，作者提出了**MINT-Bench**，一个全面的多语言基准测试。其核心方法包括：1）一个基于10种原子声学属性的**分层多轴分类法**，系统性地组织了从简单到复杂（ https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-neural-encoding-detection-is-not-all-you-need-for/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-neural-encoding-detection-is-not-all-you-need-for/ 这篇综述论文的核心贡献在于**揭示并论证了当前合成语音检测领域的一个关键误区：过度依赖“神经编码检测”**。论文首先系统回顾了基于SincNet、自监督学习（SSL）和神经编码检测的三类数据驱动方法，指出当前性能最佳的SSL模型实际上主要捕捉的是声码器（vocoder）在波形生成阶段引入的痕迹，而非 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-vibe-voice-induced-open-ended-bias-evaluation-for/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-vibe-voice-induced-open-ended-bias-evaluation-for/ 这篇论文旨在解决大型音频语言模型（LALM）在开放生成任务中社会偏见评估不足的问题。现有基准多依赖合成语音和选择题（MCQ），无法捕捉模型在真实交互中自然流露的刻板印象。为此，作者提出了**VIBE**框架，其核心是使用**真实人声录音**输入模型，并通过**开放生成任务**（如故事创作、个性化推荐 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-where-do-self-supervised-speech-models-become/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-where-do-self-supervised-speech-models-become/ 这篇论文旨在探究自监督语音模型（S3M）的不公平性究竟在模型的哪个层级产生。研究团队采用了一种轻量级的线性探针方法，在多个S3M（如WavLM, Wav2Vec2, BEST-RQ, Whisper）的每一层嵌入上，同时评估了说话人识别（SID）和自动语音识别（ASR）任务的整体性能及对不同说话人组 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-elucidating-the-snr-t-bias-of-diffusion/ Mon, 20 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-elucidating-the-snr-t-bias-of-diffusion/ 这篇论文的核心贡献是识别并系统分析了扩散概率模型（DPMs）中一个基础性问题——信噪比-时间步（SNR-t）偏差。该偏差指推理时去噪样本的实际SNR与其所分配时间步t所理论对应的SNR不匹配，这种错位源于训练时的严格耦合在推理时被累积误差打破。作者通过详实的实验（滑动窗口测试、前向与反向过程对比）揭 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-interactive-asr-towards-human-like-interaction/ Mon, 20 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-interactive-asr-towards-human-like-interaction/ 这篇论文针对传统ASR的两大盲区——WER指标对语义错误不敏感、以及系统无法通过自然交互进行纠错——提出了Interactive ASR框架。首先，作者引入S²ER（Sentence-level Semantic Error Rate），利用LLM-as-a-Judge二元判断识别结果与参考文本是否 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-the-acoustic-camouflage-phenomenon-re-evaluating/ Mon, 20 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-the-acoustic-camouflage-phenomenon-re-evaluating/ 本研究探讨了在企业财报电话会议中，副语言声学特征（音高、抖动、停顿等）对预测灾难性股价下跌的效用。作者基于MAEC数据集，提取了两种模态的特征：文本端使用FinBERT计算脚本化开场白与即兴Q&A之间的情感极性差异（Sentiment Delta），音频端提取临床语音压力标记的方差特征（音高方差、抖