语音大模型 on 语音/音频论文速递 https://nanless.github.io/audio-paper-digest-blog/tags/%E8%AF%AD%E9%9F%B3%E5%A4%A7%E6%A8%A1%E5%9E%8B/ Recent content in 语音大模型 on 语音/音频论文速递 Hugo zh-cn Wed, 29 Apr 2026 00:00:00 +0000 Adapting Diarization-Conditioned Whisper for End-to-End Multi-Talker Speech Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-adapting-diarization-conditioned-whisper-for-end/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-adapting-diarization-conditioned-whisper-for-end/ 语音识别 | 7.5/10 Advancing LLM-Based Multi-Channel Multi-Speaker Speech Recognition with Global Cross-Channel Attention and Sentence-Ordered First-In First-Out Serialized Output Training https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-advancing-llm-based-multi-channel-multi-speaker/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-advancing-llm-based-multi-channel-multi-speaker/ 语音识别 | 7.5/10 Advancing Speech Understanding in Speech-Aware Language Models with GRPO https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-advancing-speech-understanding-in-speech-aware/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-advancing-speech-understanding-in-speech-aware/ 语音问答 | 7.0/10 Adversarial Fine-Tuning on Speech Foundation Model with Vulnerable Attention Consistency Regularization for Robust Speech Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-adversarial-fine-tuning-on-speech-foundation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-adversarial-fine-tuning-on-speech-foundation/ 语音识别 | 7.5/10 Aligning Generative Speech Enhancement with Perceptual Feedback 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 Attention-Weighted Centered Kernel Alignment for Knowledge Distillation in Large Audio-Language Models Applied To Speech Emotion Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attention-weighted-centered-kernel-alignment-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attention-weighted-centered-kernel-alignment-for/ 语音情感识别 | 8.0/10 Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-text System https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attention2probability-attention-driven/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attention2probability-attention-driven/ 语音识别 | 7.0/10 Auden-Voice: General-Purpose Voice Encoder for Speech and Language Understanding https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-auden-voice-general-purpose-voice-encoder-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-auden-voice-general-purpose-voice-encoder-for/ 语音编码器 | 7.5/10 Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-audio-conditioned-diffusion-llms-for-asr-and/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-audio-conditioned-diffusion-llms-for-asr-and/ 语音识别 | 7.0/10 Behind the Scenes: Mechanistic Interpretability of Lora-Adapted Whisper for Speech Emotion Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-behind-the-scenes-mechanistic-interpretability-of/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-behind-the-scenes-mechanistic-interpretability-of/ 语音情感识别 | 7.5/10 Benchmarking Humans And Machines On Complex Multilingual Speech Understanding Tasks 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 CCST: Cross-Modal and Consistency-Aware Self-Training for Source-Free Unsupervised Domain Adaptation in Speech Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ccst-cross-modal-and-consistency-aware-self/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ccst-cross-modal-and-consistency-aware-self/ 语音识别 | 7.5/10 Contextual Biasing for ASR in Speech LLM with Common Word Cues and Bias Word Position Prediction https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-contextual-biasing-for-asr-in-speech-llm-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-contextual-biasing-for-asr-in-speech-llm-with/ 语音识别 | 7.0/10 Cross-Lingual Alzheimer’s Disease Detection with Multimodal LLMs via Speech Cue-Augmented Prompting and Instruction Tuning https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cross-lingual-alzheimers-disease-detection-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cross-lingual-alzheimers-disease-detection-with/ 语音生物标志物 | 6.5/10 Cross-Lingual Interleaving for Speech Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cross-lingual-interleaving-for-speech-language/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cross-lingual-interleaving-for-speech-language/ 语音大模型 | 7.5/10 Cross-Modal Knowledge Distillation for Speech Large Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cross-modal-knowledge-distillation-for-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cross-modal-knowledge-distillation-for-speech/ 语音大模型 | 7.0/10 Direct Simultaneous Translation Activation for Large Audio-Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-direct-simultaneous-translation-activation-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-direct-simultaneous-translation-activation-for/ 语音翻译 | 6.0/10 Do Bias Benchmarks Generalise? Evidence from Voice-Based Evaluation of Gender Bias in Speechllms 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 Do Speech LLMs Learn Crossmodal Embedding Spaces? 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 Enhancing Dialogue-Related Speech Tasks with Generated Spoken Dialogues https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-dialogue-related-speech-tasks-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-dialogue-related-speech-tasks-with/ 语音对话系统 | 6.5/10 Enhancing Speaker Verification with w2v-BERT 2.0 and Knowledge Distillation Guided Structured Pruning https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-speaker-verification-with-w2v-bert-20/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-enhancing-speaker-verification-with-w2v-bert-20/ 说话人验证 | 7.5/10 Evaluating Bias in Spoken Dialogue LLMs for Real-World Decisions and Recommendations 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 Evaluating Emotion Recognition in Spoken Language Models on Emotionally Incongruent Speech 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 Fine-Tuning Large Multimodal Models for Automatic Pronunciation Assessment https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fine-tuning-large-multimodal-models-for-automatic/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fine-tuning-large-multimodal-models-for-automatic/ 语音评估 | 7.0/10 FinHuBERT: Hierarchical Feature Imitating Networks for Low-Resource Speech Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-finhubert-hierarchical-feature-imitating-networks/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-finhubert-hierarchical-feature-imitating-networks/ 语音识别 | 7.5/10 FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-focalcodec-stream-streaming-low-bitrate-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-focalcodec-stream-streaming-low-bitrate-speech/ 语音编码 | 8.0/10 Frame-Stacked Local Transformers for Efficient Multi-Codebook Speech Generation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-frame-stacked-local-transformers-for-efficient/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-frame-stacked-local-transformers-for-efficient/ 语音合成 | 7.5/10 From Human Speech to Ocean Signals: Transferring Speech Large Models for Underwater Acoustic Target Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-from-human-speech-to-ocean-signals-transferring/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-from-human-speech-to-ocean-signals-transferring/ 水下声学目标识别 | 7.0/10 Game-Time: Evaluating Temporal Dynamics in Spoken Language Models 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 Grey-Box Prompt Tuning With Graph Alignment for Speech-Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-grey-box-prompt-tuning-with-graph-alignment-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-grey-box-prompt-tuning-with-graph-alignment-for/ 语音识别 | 8.0/10 Group Relative Policy Optimization for Text-to-Speech with Large Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-group-relative-policy-optimization-for-text-to/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-group-relative-policy-optimization-for-text-to/ 语音合成 | 8.0/10 High-Fidelity Speech Enhancement Via Discrete Audio Tokens https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-high-fidelity-speech-enhancement-via-discrete/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-high-fidelity-speech-enhancement-via-discrete/ 语音增强 | 7.5/10 Human-1 by Josh Talks: A Full-Duplex Conversational Modeling Framework in Hindi using Real-World Conversations https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-human-1-by-josh-talks-a-full-duplex/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-human-1-by-josh-talks-a-full-duplex/ 语音对话系统 | 7.5/10 ICASSP 2026 - 语音大模型 论文列表 https://nanless.github.io/audio-paper-digest-blog/posts/icassp2026-task-064/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/icassp2026-task-064/ 共 3 篇 ICASSP 2026 语音大模型 方向论文 In-Sync: Adaptation of Speech Aware Large Language Models for ASR with Word level timestamp predictions https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-in-sync-adaptation-of-speech-aware-large-language/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-in-sync-adaptation-of-speech-aware-large-language/ 语音识别 | 7.0/10 Leveraging Large Speech Language Models as Evaluators for Expressive Speech 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 Leveraging Segment-Level Speech Representations for LLM-Based Speech Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-segment-level-speech-representations/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-leveraging-segment-level-speech-representations/ 语音识别 | 7.0/10 MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large Audio-Language Model https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mi-fuse-label-fusion-for-unsupervised-domain/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mi-fuse-label-fusion-for-unsupervised-domain/ 语音情感识别 | 8.0/10 Mispronunciation Detection and Diagnosis Without Model Training: A Retrieval-Based Approach https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mispronunciation-detection-and-diagnosis-without/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mispronunciation-detection-and-diagnosis-without/ 语音评估 | 8.0/10 Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mitigating-attention-sinks-and-massive/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mitigating-attention-sinks-and-massive/ 语音识别 | 7.0/10 MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speech https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mnv-17-a-high-quality-performative-mandarin/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mnv-17-a-high-quality-performative-mandarin/ 语音识别 | 7.5/10 MSF-SER: Enriching Acoustic Modeling with Multi-Granularity Semantics for Speech Emotion Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-msf-ser-enriching-acoustic-modeling-with-multi/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-msf-ser-enriching-acoustic-modeling-with-multi/ 语音情感识别 | 7.5/10 MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-Token Prediction https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mtp-s2ut-enhancing-speech-to-speech-translation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mtp-s2ut-enhancing-speech-to-speech-translation/ 语音翻译 | 8.5/10 Optimizing Speech Language Models for Acoustic Consistency 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 PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-personaplex-voice-and-role-control-for-full/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-personaplex-voice-and-role-control-for-full/ 语音对话系统 | 8.5/10 Plug-and-Play Emotion Graphs for Compositional Prompting in Zero-Shot Speech Emotion Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-plug-and-play-emotion-graphs-for-compositional/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-plug-and-play-emotion-graphs-for-compositional/ 语音情感识别 | 7.0/10 Principled Coarse-Grained Acceptance For Speculative Decoding In Speech https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-principled-coarse-grained-acceptance-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-principled-coarse-grained-acceptance-for/ 语音合成 | 7.5/10 Proficiency-Aware Adaptation and Data Augmentation for Robust L2 ASR https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-proficiency-aware-adaptation-and-data/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-proficiency-aware-adaptation-and-data/ 语音识别 | 6.5/10 Reducing Prompt Sensitivity in LLM-Based Speech Recognition Through Learnable Projection https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-reducing-prompt-sensitivity-in-llm-based-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-reducing-prompt-sensitivity-in-llm-based-speech/ 语音识别 | 7.0/10 Reference-Aware SFM Layers for Intrusive Intelligibility Prediction 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 Relative Time Intervals Representation For Word-Level Timestamping With Masked Training https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-relative-time-intervals-representation-for-word/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-relative-time-intervals-representation-for-word/ 语音识别 | 8.0/10 Revisiting Direct Speech-to-Text Translation with Speech LLMS: Better Scaling than Cot Prompting? https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-revisiting-direct-speech-to-text-translation-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-revisiting-direct-speech-to-text-translation-with/ 语音翻译 | 7.5/10 RLBR: Reinforcement Learning with Biasing Rewards for Contextual Speech Large Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-rlbr-reinforcement-learning-with-biasing-rewards/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-rlbr-reinforcement-learning-with-biasing-rewards/ 语音识别 | 8.0/10 Scaling Spoken Language Models with Syllabic Speech Tokenization https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-scaling-spoken-language-models-with-syllabic/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-scaling-spoken-language-models-with-syllabic/ 语音理解 | 7.0/10 SED: Structural Entropy Based Speech Discretization for Discrete Token-Based ASR https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sed-structural-entropy-based-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sed-structural-entropy-based-speech/ 语音识别 | 6.5/10 Session-Level Spoken Language Assessment with A Multimodal Foundation Model Via Multi-Target Learning https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-session-level-spoken-language-assessment-with-a/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-session-level-spoken-language-assessment-with-a/ 语音评估 | 7.5/10 SLM-SS: Speech Language Model for Generative Speech Separation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-slm-ss-speech-language-model-for-generative/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-slm-ss-speech-language-model-for-generative/ 语音分离 | 7.5/10 SLM-TTA: A Framework for Test-Time Adaptation of Generative Spoken Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-slm-tta-a-framework-for-test-time-adaptation-of/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-slm-tta-a-framework-for-test-time-adaptation-of/ 语音识别 | 7.0/10 Slot Filling as a Reasoning Task for Speechllms https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-slot-filling-as-a-reasoning-task-for-speechllms/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-slot-filling-as-a-reasoning-task-for-speechllms/ 槽填充 | 6.5/10 Speaker Anonymisation for Speech-Based Suicide Risk Detection https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-speaker-anonymisation-for-speech-based-suicide/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-speaker-anonymisation-for-speech-based-suicide/ 语音匿名化 | 7.5/10 SpeechMapper: Speech-To-Text Embedding Projector for LLMs https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-speechmapper-speech-to-text-embedding-projector/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-speechmapper-speech-to-text-embedding-projector/ 语音大模型 | 7.0/10 SSVD-O: Parameter-Efficient Fine-Tuning with Structured SVD for Speech Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ssvd-o-parameter-efficient-fine-tuning-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ssvd-o-parameter-efficient-fine-tuning-with/ 语音识别 | 7.0/10 Step-Audio-R1.5 Technical Report 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 Streaming Speech Recognition with Decoder-Only Large Language Models and Latency Optimization https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-streaming-speech-recognition-with-decoder-only/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-streaming-speech-recognition-with-decoder-only/ 语音识别 | 7.0/10 StyleBench: Evaluating Speech Language Models on Conversational Speaking Style Control 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 T-Cache: Fast Inference For Masked Generative Transformer-Based TTS Via Prompt-Aware Feature Caching https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-t-cache-fast-inference-for-masked-generative/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-t-cache-fast-inference-for-masked-generative/ 语音合成 | 9.0/10 Target-Speaker LLM-ASR with Speaker-Aware Speech Encoder https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-target-speaker-llm-asr-with-speaker-aware-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-target-speaker-llm-asr-with-speaker-aware-speech/ 语音识别 | 8.8/10 TASU: Text-only Alignment for Speech Understanding https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tasu-text-only-alignment-for-speech-understanding/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tasu-text-only-alignment-for-speech-understanding/ 语音识别 | 7.0/10 TICL: Text-Embedding KNN for Speech in-Context Learning Unlocks Speech Recognition Abilities of Large Multimodal Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ticl-text-embedding-knn-for-speech-in-context/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ticl-text-embedding-knn-for-speech-in-context/ 语音识别 | 7.5/10 Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-building-speech-large-language-models-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-towards-building-speech-large-language-models-for/ 语音识别 | 6.5/10 Train Short, Infer Long: Speech-LLM Enables Zero-Shot Streamable Joint ASR and Diarization on Long Audio https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-train-short-infer-long-speech-llm-enables-zero/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-train-short-infer-long-speech-llm-enables-zero/ 说话人分离 | 9.0/10 Two-Stage Language Model Framework for Acoustic Echo Cancellation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-two-stage-language-model-framework-for-acoustic/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-two-stage-language-model-framework-for-acoustic/ 语音增强 | 7.5/10 UJCodec: An End-to-end Unet-Style Codec for Joint Speech Compression and Enhancement https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ujcodec-an-end-to-end-unet-style-codec-for-joint/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ujcodec-an-end-to-end-unet-style-codec-for-joint/ 语音增强 | 7.5/10 Understanding Textual Capability Degradation in Speech LLMS via Parameter Importance Analysis https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-understanding-textual-capability-degradation-in/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-understanding-textual-capability-degradation-in/ 语音问答 | 7.5/10 Vocalnet-M2: Advancing Low-Latency Spoken Language Modeling via Integrated Multi-Codebook Tokenization and Multi-Token Prediction https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-vocalnet-m2-advancing-low-latency-spoken-language/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-vocalnet-m2-advancing-low-latency-spoken-language/ 语音对话系统 | 7.5/10 WAV2LEV: Predicting Levenshtein Edit Operation Sequences For Fine-Grained Estimation of Automatic Speech Recognition Error 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 Whisper-MLA: Reducing GPU Memory Consumption of ASR Models Based on MHA2MLA Conversion https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-whisper-mla-reducing-gpu-memory-consumption-of/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-whisper-mla-reducing-gpu-memory-consumption-of/ 语音识别 | 7.0/10 Whisper-QF: Leveraging Dual Cross-Attention Q-Former for Speech Emotion Recognition With Multi-Task Learning https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-whisper-qf-leveraging-dual-cross-attention-q/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-whisper-qf-leveraging-dual-cross-attention-q/ 语音情感识别 | 7.5/10 Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective 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 Z-Scores: A Metric for Linguistically Assessing Disfluency Removal 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 Scaling Properties of Continuous Diffusion Spoken Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-scaling-properties-of-continuous-diffusion-spoken/ Tue, 28 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-scaling-properties-of-continuous-diffusion-spoken/ 语音生成 | 8.0/10 MAGIC-TTS: Fine-Grained Controllable Speech Synthesis with Explicit Local Duration and Pause Control https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-25-magic-tts-fine-grained-controllable-speech/ Sat, 25 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-25-magic-tts-fine-grained-controllable-speech/ 语音合成 | 7.5/10 语音/音频论文速递 2026-04-25 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-25/ Sat, 25 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-25/ 共分析 2 篇语音/AI 论文 Do LLM Decoders Listen Fairly? Benchmarking How Language Model Priors Shape Bias in Speech Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-do-llm-decoders-listen-fairly-benchmarking-how/ Fri, 24 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-do-llm-decoders-listen-fairly-benchmarking-how/ 语音识别 | 7.5/10 Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-indic-codecfake-meets-satyam-towards-detecting/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-indic-codecfake-meets-satyam-towards-detecting/ 1. **问题**：现有针对基于神经音频编解码器的语音深度伪造（CodecFake）检测的研究主要集中在英语和中文，对于语言多样性极高的印度语言缺乏大规模的基准数据集和有效的检测方法。 2. **方法**：作者构建了首个大规模印度语言CodecFake数据集（ICF），并提出了一个名为SATYA SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation 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 Towards Streaming Target Speaker Extraction via Chunk-wise Interleaved Splicing of Autoregressive Language Model https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-towards-streaming-target-speaker-extraction-via/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-towards-streaming-target-speaker-extraction-via/ 1. **要解决什么问题**：现有基于生成模型（如扩散模型、自回归模型）的目标说话人提取（TSE）方法依赖全局上下文，难以直接用于实时流式场景，强行适配会导致性能严重下降。 2. **方法核心是什么**：提出首个面向流式TSE的自回归（AR）框架，核心是“分块交错拼接范式”。该范式将混合语音分块 MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models 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 MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-moshirag-asynchronous-knowledge-retrieval-for/ Mon, 20 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-moshirag-asynchronous-knowledge-retrieval-for/ 本文旨在解决全双工语音语言模型（如Moshi）事实性不足的核心问题，同时不牺牲其高交互性。**问题**：全双工模型能实时打断和回应，但因训练数据规模远小于文本，其知识储备和事实准确性较弱。**方法**：提出了MoshiRAG，一个模块化框架。它在Moshi模型中引入一个特殊的`<ret>`检索触发令 VoxMind: An End-to-End Agentic Spoken Dialogue System https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-voxmind-an-end-to-end-agentic-spoken-dialogue/ Mon, 20 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-voxmind-an-end-to-end-agentic-spoken-dialogue/ 端到端语音对话模型在自然交互上进步迅速，但普遍缺乏处理复杂任务的agent能力（工具调用、规划、推理）。本文首先形式化定义了"端到端语音智能体"的四大维度——画像（Profile）、记忆（Memory）、规划（Planning）与执行（Action Execution），填补了该领域理论标准的空白。 Contextual Biasing for ASR in Speech LLM with Common Word Cues and Bias Word Position Prediction https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-contextual-biasing-for-asr-in-speech-llm-with/ Sun, 19 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-contextual-biasing-for-asr-in-speech-llm-with/ 这篇论文旨在解决语音大模型（SLLM）在识别训练数据中稀有或未见的“偏置词”时性能不佳的问题。传统方法依赖于为偏置词提供精确的音素序列（通过G2P系统生成），但这对用户有专业要求且工具兼容性差。为此， VoxSafeBench: Not Just What Is Said, but Who, How, and Where https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-voxsafebench-not-just-what-is-said-but-who-how/ Sun, 19 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-voxsafebench-not-just-what-is-said-but-who-how/ 这篇论文旨在解决一个关键问题：当语音大模型（SLM）进入多用户共享环境时，仅基于文本内容的安全对齐策略是不足的，说话人身份、副语言特征和声学场景等音频上下文信息会根本性地改变请求的性质。为此，作者提出