Posts

ICASSP 2026 - 语音克隆论文列表

ICASSP 2026 - 语音克隆共 4 篇论文 ← 返回 ICASSP 2026 总览排名论文评分分档 🥇 VoxMorph: Scalable Zero-Shot Voice Identity Morphing via Dis 9.0分前10% 🥈 FED-PISA: Federated Voice Cloning Via Personalized Identity- 8.0分前25% 🥉 Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Clonin 7.5分前25% 4. ZSV2C-MLLM: Zero-Shot Visual Voice Cloning Via Multimodal La 6.5分前50% 📋 论文详情 🥇 VoxMorph: Scalable Zero-Shot Voice Identity Morphing via Disentangled Embeddings 🔥 9.0/10 | 前10% | #语音克隆 | #流匹配 | #零样本 #语音合成 ...

ICASSP 2026 - 语音分离论文列表

ICASSP 2026 - 语音分离共 25 篇论文 ← 返回 ICASSP 2026 总览排名论文评分分档 🥇 Adaptive Rotary Steering with Joint Autoregression for Robus 8.5分前25% 🥈 UNMIXX: Untangling Highly Correlated Singing Voices Mixtures 8.5分前25% 🥉 Brainprint-Modulated Target Speaker Extraction 8.0分前25% 4. Flexio: Flexible Single- and Multi-Channel Speech Separation 8.0分前25% 5. MMAudioSep: Taming Video-to-Audio Generative Model Towards V 8.0分前25% 6. Bayesian Signal Separation Via Plug-and-Play Diffusion-Withi 7.5分前25% 7. An Audio-Visual Speech Separation Network with Joint Cross-A 7.5分前25% 8. Aneural Forward Filtering for Speaker-Image Separation 7.5分前25% 9. Str-DiffSep: Streamable Diffusion Model for Speech Separatio 7.5分前25% 10. PromptSep: Generative Audio Separation Via Multimodal Prompt 7.5分前10% 11. Diff-vs: Efficient Audio-Aware Diffusion U-Net for Vocals Se 7.5分前25% 12. CodeSep: Low-Bitrate Codec-Driven Speech Separation with Bas 7.5分前25% 13. SLM-SS: Speech Language Model for Generative Speech Separati 7.5分前25% 14. VM-UNSSOR: Unsupervised Neural Speech Separation Enhanced by 7.5分前25% 15. SoundCompass: Navigating Target Sound Extraction with Effect 7.5分前25% 16. Prototype-Guided Cross-Modal Contrastive Learning for Contin 7.5分前25% 17. EEG and Eye-Tracking Driven Dynamic Target Speaker Extractio 7.0分前25% 18. Robust Online Overdetermined Independent Vector Analysis Bas 7.0分前25% 19. AR-BSNet: Towards Ultra-Low Complexity Autoregressive Target 7.0分前25% 20. Spectral or Spatial? Leveraging Both for Speaker Extraction 7.0分前25% 21. Neural Network-Based Time-Frequency-Bin-Wise Linear Combinat 7.0分前25% 22. Training Dynamics-Aware Multi-Factor Curriculum Learning for 7.0分前25% 23. Vib2Sound: Separation Of Multimodal Sound Sources 6.5分前50% 24. Source Separation For A Cappella Music 6.5分前50% 25. Towards Distance-Aware Synthetic Audio Mixtures for Universa 6.5分前50% 📋 论文详情 🥇 Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarios 🔥 8.5/10 | 前25% | #语音分离 | #信号处理 | #麦克风阵列 #自回归模型 ...

ICASSP 2026 - 语音匿名化论文列表

ICASSP 2026 - 语音匿名化共 10 篇论文 ← 返回 ICASSP 2026 总览排名论文评分分档 🥇 ECSA: Dual-Branch Emotion Compensation for Emotion-Consisten 8.5分前25% 🥈 Target Speaker Anonymization in Multi-Speaker Recordings 7.6分前50% 🥉 Content Anonymization for Privacy in Long-Form Audio 7.5分前25% 4. Content Leakage in Librispeech and its Impact on the Privacy 7.5分前25% 5. Improving the Speaker Anonymization Evaluation’s Robustness 7.5分前50% 6. ZK-VSA: Zero-Knowledge Verifiable Speaker Anonymization Leve 7.5分前25% 7. Speaker Anonymisation for Speech-Based Suicide Risk Detectio 7.5分前25% 8. PRSA: Preventing Malicious Speaker Recognition and Speech Sy 7.0分前25% 9. Stream-Voice-Anon: Enhancing Utility of Real-Time Speaker An 7.0分前25% 10. Identity Leakage Through Accent Cues in Voice Anonymisation 7.0分前50% 📋 论文详情 🥇 ECSA: Dual-Branch Emotion Compensation for Emotion-Consistent Speaker Anonymization 🔥 8.5/10 | 前25% | #语音匿名化 | #生成模型 | #语音情感识别 #自监督学习 ...

ICASSP 2026 - 语音发现论文列表

ICASSP 2026 - 语音发现共 1 篇论文 ← 返回 ICASSP 2026 总览排名论文评分分档 🥇 Unsupervised Lexicon Learning from Speech is Limited by Repr 8.0分前25% 📋 论文详情 🥇 Unsupervised Lexicon Learning from Speech is Limited by Representations Rather than Clustering 🔥 8.0/10 | 前25% | #语音发现 | #聚类 | #自监督学习 #零资源 👥 作者与机构第一作者：Danel Slabbert（斯泰伦博斯大学电气与电子工程系）通讯作者：Herman Kamper（斯泰伦博斯大学电气与电子工程系）作者列表：Danel Slabbert（斯泰伦博斯大学电气与电子工程系），Simon Malan（斯泰伦博斯大学电气与电子工程系），Herman Kamper（斯泰伦博斯大学电气与电子工程系） 💡 毒舌点评这篇论文的亮点在于其精巧的控制实验设计，通过人为理想化聚类初始化或表示一致性，清晰地量化了“表示变异性”与“聚类方法”对最终词汇学习性能的独立影响，为领域指明了瓶颈所在。然而，其短板也很明显：研究完全依赖于理想的词边界已知前提，这在真实的零资源场景中不存在，因此结论的实践指导意义有所折扣，本质上仍是一篇在“温室”条件下的诊断性研究。 🔗 开源详情代码：论文中未提及代码链接。模型权重：未提及作者自己的模型权重，但明确使用了公开的预训练SSL模型（如WavLM Large, HuBERT Large, mHuBERT等）。数据集：使用了公开的标准数据集（LibriSpeech, Zero Speech Challenge数据）。 Demo：未提及。复现材料：论文详细说明了特征提取层、PCA维度、量化器训练数据、聚类超参数等，为复现提供了详细指南。运行时间的报告有助于评估计算成本。引用的开源项目/模型：FAISS (Facebook Research), scikit-learn, igraph, Montreal Forced Aligner。SSL模型来自Hugging Face模型库（HuBERT, WavLM, mHuBERT）。总体开源情况：论文本身未提供完整代码包，但其复现高度依赖并整合了现有的开源模型和工具，给出了清晰的组合和配置指南。 📌 核心摘要 ...

ICASSP 2026 - 语音合成论文列表

ICASSP 2026 - 语音合成共 63 篇论文 ← 返回 ICASSP 2026 总览排名论文评分分档 🥇 T-Cache: Fast Inference For Masked Generative Transformer-Ba 9.0分前25% 🥈 Wavenext 2: Convnext-Based Fast Neural Vocoders with Residua 9.0分前25% 🥉 VoXtream: Full-Stream Text-To-Speech With Extremely Low Late 8.5分前25% 4. EMORL-TTS: Reinforcement Learning for Fine-Grained Emotion C 8.5分前25% 5. No Verifiable Reward for Prosody: Toward Preference-Guided P 8.0分前25% 6. Marco-Voice: A Unified Framework for Expressive Speech Synth 8.0分前25% 7. Neuromamba: Adaptive Frequency Filtering with a Pyramid Mamb 8.0分前25% 8. Group Relative Policy Optimization for Text-to-Speech with L 8.0分前25% 9. Do You Hear What I Mean? Quantifying the Instruction-Percept 8.0分前25% 10. OV-INSTRUCTTTS: Towards Open-Vocabulary Instruct Text-to-Spe 8.0分前25% 11. HD-PPT: Hierarchical Decoding of Content- and Prompt-Prefere 8.0分前25% 12. Emotion-Aligned Generation in Diffusion Text to Speech Model 8.0分前25% 13. Measuring Prosody Diversity in Zero-Shot TTS: A New Metric, 8.0分前25% 14. DAIEN-TTS: Disentangled Audio Infilling for Environment-Awar 8.0分前25% 15. BridgeCode: A Dual Speech Representation Paradigm for Autore 8.0分前25% 16. Continuous-Token Diffusion for Speaker-Referenced TTS in Mul 8.0分前10% 17. Prosody-Guided Harmonic Attention for Phase-Coherent Neural 8.0分前25% 18. Optimizing Speech Language Models for Acoustic Consistency 8.0分前25% 19. NCF-TTS: Enhancing Flow Matching Based Text-To-Speech with N 8.0分前25% 20. ARCHI-TTS: A Flow-Matching-Based Text-to-Speech Model with S 8.0分前25% 21. EMG-to-Speech with Fewer Channels 7.5分前25% 22. VividTalker: A Modular Framework for Expressive 3D Talking A 7.5分前25% 23. Real-Time Streaming MEL Vocoding with Generative Flow Matchi 7.5分前25% 24. From Hallucination to Articulation: Language Model-Driven Lo 7.5分前25% 25. SynParaSpeech: Automated Synthesis of Paralinguistic Dataset 7.5分前25% 26. Asynchrony-Aware Decoupled Multimodal Control for Cued Speec 7.5分前10% 27. DMP-TTS: Disentangled Multi-Modal Prompting for Controllable 7.5分前25% 28. RRPO: Robust Reward Policy Optimization for LLM-Based Emotio 7.5分前25% 29. Syncspeech: Efficient and Low-Latency Text-to-Speech Based o 7.5分前25% 30. Principled Coarse-Grained Acceptance For Speculative Decodin 7.5分前25% 31. SPADE: Structured Pruning and Adaptive Distillation for Effi 7.5分前25% 32. Entropy-Guided GRVQ for Ultra-Low Bitrate Neural Speech Code 7.5分前25% 33. Discrete Diffusion for Generative Modeling of Text-Aligned S 7.5分前25% 34. Emotional Dimension Control in Language Model-Based Text-To- 7.5分前25% 35. Beyond Global Emotion: Fine-Grained Emotional Speech Synthes 7.5分前25% 36. QFOCUS: Controllable Synthesis for Automated Speech Stress E 7.5分前50% 37. Synthetic yet Striking? Assessing Vocal Charisma in TTS via 7.5分前25% 38. TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Fram 7.5分前25% 39. Deep Dubbing: End-to-End Auto-Audiobook System with Text-to- 7.5分前25% 40. Erasing Your Voice Before it’s Heard: Training-Free Speaker 7.5分前25% 41. InstructAudio: Unified Speech and Music Generation with Natu 7.5分前25% 42. GLA-GRAD++: An Improved Griffin-Lim Guided Diffusion Model f 7.5分前25% 43. Int-MeanFlow: Few-Step Speech Generation with Integral Veloc 7.5分前25% 44. Training Flow Matching Models with Reliable Labels via Self- 7.5分前25% 45. Hierarchical Discrete Flow Matching For Multi-Codebook Codec 7.5分前25% 46. Frame-Stacked Local Transformers for Efficient Multi-Codeboo 7.5分前25% 47. Direct Preference Optimization For Speech Autoregressive Dif 7.5分前25% 48. MirrorTalk: Forging Personalized Avatars Via Disentangled St 7.0分前25% 49. Residual Tokens Enhance Masked Autoencoders for Speech Model 7.0分前50% 50. SP-MCQA: Evaluating Intelligibility of TTS Beyond the Word L 7.0分前50% 51. SPAM: Style Prompt Adherence Metric for Prompt-Based TTS 7.0分前50% 52. Gelina: Unified Speech and Gesture Synthesis Via Interleaved 7.0分前50% 53. Retrieval-Based Speculative Decoding For Autoregressive Spee 7.0分前50% 54. T-Mimi: A Transformer-Based Mimi Decoder for Real-Time On-Ph 7.0分前50% 55. Wave-Trainer-Fit: Neural Vocoder With Trainable Prior And Fi 7.0分前25% 56. EmoShift: Lightweight Activation Steering for Enhanced Emoti 7.0分前50% 57. Task Vector in TTS: Toward Emotionally Expressive Dialectal 7.0分前50% 58. Quantifying Speaker Embedding Phonological Rule Interactions 7.0分前25% 59. PFluxTTS: Hybrid Flow-Matching TTS with Robust Cross-Lingual 7.0分前50% 60. LP-CFM: Perceptual Invariance-Aware Conditional Flow Matchin 7.0分前25% 61. SFM-TTS: Lightweight and Rapid Speech Synthesis with Flexibl 7.0分前25% 62. MELA-TTS: Joint Transformer-Diffusion Model with Representat 7.0分前25% 63. Combining Multi-Order Attention and Multi-Resolution Discrim 6.5分前50% 📋 论文详情 🥇 T-Cache: Fast Inference For Masked Generative Transformer-Based TTS Via Prompt-Aware Feature Caching 🔥 9.0/10 | 前25% | #语音合成 | #实时处理 | #零样本 #语音大模型 ...

ICASSP 2026 - 语音增强 #对抗防御论文列表

ICASSP 2026 - 语音增强 #对抗防御共 1 篇论文 ← 返回 ICASSP 2026 总览排名论文评分分档 🥇 Adversarial Defense via Generative Speech Enhancement Module 7.5分前25% 📋 论文详情 🥇 Adversarial Defense via Generative Speech Enhancement Module ✅ 7.5/10 | 前25% | #语音增强 #对抗防御 | #语音增强 #数据增强 | #语音增强 #对抗防御 👥 作者与机构第一作者：未说明通讯作者：未说明作者列表：Chi-Tao Chen（国立中央大学资讯工程学系），Chun-Shien Lu（中央研究院资讯科技研究所），Jia-Ching Wang（国立中央大学资讯工程学系） 💡 毒舌点评本文巧妙地将对抗防御问题转化为语音增强任务，使用一个轻量级（2M参数）且高效的生成模型（MP-SENet）实现了在多个数据集和攻击类型下的出色防御效果，推理速度远超基于扩散模型的竞品。然而，其核心防御机制（高斯噪声注入+增强）在理论上可能不够“坚固”，面对精心设计的自适应攻击时（如论文表5），性能仍有显著下降，且在SC09这一基准上并未超越最强的对比方法AudioPure。 🔗 开源详情代码：提供了官方GitHub仓库链接：apoman123/SpeechEnhancementDefense。模型权重：论文中提及使用了在DNS Challenge上预训练的MP-SENet模型，但未明确是否公开其微调后的防御专用权重。数据集：使用了公开数据集：SC09（Google Speech Commands子集）， VCTK， QKWS， DNS-Challenge。 Demo：未提及。复现材料：给出了关键的训练数据增强细节（噪声dBFS范围及最优值）、损失函数公式与权重、攻击参数设置。但优化器、学习率等训练配置未说明。引用的开源项目：依赖了公开模型MP-SENet，并引用了多个基线方法和攻击方法的开源实现（如DefenseGAN, AudioPure, PGD攻击代码等）。 📌 核心摘要 ...

ICASSP 2026 - 语音增强论文列表

ICASSP 2026 - 语音增强共 75 篇论文 ← 返回 ICASSP 2026 总览排名论文评分分档 🥇 A Lightweight Fourier-Based Network for Binaural Speech Enha 8.5分前25% 🥈 DiTSE: High-Fidelity Generative Speech Enhancement via Laten 8.5分前10% 🥉 Towards Lightweight Adaptation of Speech Enhancement Models 8.5分前25% 4. FastEnhancer: Speed-Optimized Streaming Neural Speech Enhanc 8.5分前25% 5. DisContSE: Single-Step Diffusion Speech Enhancement based on 8.5分前10% 6. Sidon: Fast and Robust Open-Source Multilingual Speech Resto 8.5分前25% 7. Spike-Driven Low-Power Speech Bandwidth Extension 8.0分前25% 8. MAGE: A Coarse-to-Fine Speech Enhancer with Masked Generativ 8.0分前25% 9. Deep Learning-Based Joint Optimization of Adaptive Feedback 8.0分前25% 10. HyFlowSE: Hybrid End-To-End Flow-Matching Speech Enhancement 8.0分前25% 11. HCGAN: Harmonic-Coupled Generative Adversarial Network for S 8.0分前50% 12. Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U 8.0分前25% 13. Mixture To Beamformed Mixture: Leveraging Beamformed Mixture 8.0分前25% 14. Modeling Strategies For Speech Enhancement in The Latent Spa 8.0分前50% 15. LAFUFU: Latent Acoustic Features For Ultra-Fast Utterance Re 8.0分前25% 16. Influence of Clean Speech Characteristics on Speech Enhancem 8.0分前25% 17. LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Si 7.5分前25% 18. MSANET: Multi-Scale Semantic Aggregation Network for Brain-A 7.5分前25% 19. Bone-Conduction Guided Multimodal Speech Enhancement with Co 7.5分前25% 20. The 3rd Clarity Prediction Challenge: A Machine Learning Cha 7.5分前25% 21. Two-Stage Language Model Framework for Acoustic Echo Cancell 7.5分前25% 22. E2E-AEC: Implementing An End-To-End Neural Network Learning 7.5分前25% 23. SpatialNet-Echo: Real-Time Acoustic Echo Cancellation via In 7.5分前25% 24. A Stabilized Hybrid Active Noise Control Algorithm of GFANC 7.5分前25% 25. Enhancing Speech Intelligibility Prediction for Hearing Aids 7.5分前25% 26. H-nnPBFDAF: Hierarchical Neural Network Partitioned Block Fr 7.5分前25% 27. Joint Deep Secondary Path Estimation and Adaptive Control fo 7.5分前25% 28. Enhancing Noise Robustness for Neural Speech Codecs Through 7.5分前25% 29. Low-Bandwidth High-Fidelity Speech Transmission with Generat 7.5分前25% 30. From Diet to Free Lunch: Estimating Auxiliary Signal Propert 7.5分前25% 31. Beamforming Using Virtual Microphones for Hearing Aid Applic 7.5分前50% 32. I-DCCRN-VAE: An Improved Deep Representation Learning Framew 7.5分前25% 33. Do We Need EMA for Diffusion-Based Speech Enhancement? Towar 7.5分前50% 34. Hair Noise Analysis and Mitigation for Smart Glasses Audio C 7.5分前25% 35. Are Modern Speech Enhancement Systems Vulnerable to Adversar 7.5分前25% 36. UJCodec: An End-to-end Unet-Style Codec for Joint Speech Com 7.5分前25% 37. Spatial Covariance Matrix Reconstruction for Speech Enhancem 7.5分前25% 38. Training-Free Inference-Time Scaling for Audio Source Separa 7.5分前25% 39. Forward Convolutive Prediction for Frame Online Monaural Spe 7.5分前50% 40. MeanFlowSE: One-Step Generative Speech Enhancement via Condi 7.5分前10% 41. FlowSE-GRPO: Training Flow Matching Speech Enhancement via O 7.5分前25% 42. Aligning Generative Speech Enhancement with Perceptual Feedb 7.5分前25% 43. PG-SE: Predictive Acceleration and Correction for Generative 7.5分前25% 44. Dynamically Slimmable Speech Enhancement Network with Metric 7.5分前25% 45. Lightweight Phoneme-Conditioned Bandwidth Extension for Body 7.5分前25% 46. Fast-ULCNet: A Fast and Ultra Low Complexity Network for Sin 7.5分前25% 47. ParaGSE: Parallel Generative Speech Enhancement with Group-V 7.5分前25% 48. High-Fidelity Speech Enhancement Via Discrete Audio Tokens 7.5分前25% 49. DISSR: Disentangling Speech Representation for Degradation-P 7.5分前25% 50. Ranking The Impact of Contextual Specialization in Neural Sp 7.5分前25% 51. BSMP-SENet:Band-Split Magnitude-Phase Network for Speech Enh 7.0分前25% 52. DECAF: Dynamic Envelope Context-Aware Fusion for Speech-Enve 7.0分前25% 53. DAT-CFTNet: Speech Enhancement for Cochlear Implant Recipien 7.0分前50% 54. Acoustic Teleportation Via Disentangled Neural Audio Codec R 7.0分前25% 55. Reference Microphone Selection for Guided Source Separation 7.0分前50% 56. Low-Latency Audio Front-End Region-of-Interest Beamforming f 7.0分前25% 57. AmbiDrop: Array-Agnostic Speech Enhancement Using Ambisonics 7.0分前50% 58. Joint Multichannel Acoustic Feedback Cancellation and Speake 7.0分前25% 59. Gdiffuse: Diffusion-Based Speech Enhancement with Noise Mode 7.0分前25% 60. An Efficient Neural Network for Modeling Human Auditory Neur 7.0分前25% 61. Shortcut Flow Matching for Speech Enhancement: Step-Invarian 7.0分前25% 62. Generalizability of Predictive and Generative Speech Enhance 7.0分前50% 63. Mambaformer: State-Space Augmented Self-Attention with Downu 7.0分前25% 64. Auditory-Inspired Transformer for Binaural Speech Enhancemen 7.0分前25% 65. A State-Dependent Markov Diffusion Process for Generative Sp 6.5分前25% 66. Confidence-Based Filtering for Speech Dataset Curation with 6.5分前50% 67. Sampling-Rate-Agnostic Speech Super-Resolution Based on Gaus 6.5分前25% 68. Low-Frequency Harmonic Control for Speech Intelligibility in 6.5分前50% 69. What the student learns in knowledge distillation: A subspac 6.5分前50% 70. MeanSE: Efficient Generative Speech Enhancement with Mean Fl 6.5分前25% 71. On The Design of Efficient Neural Methods for Geometry-Agnos 6.5分前50% 72. Position-Invariant Fine-Tuning Of Speech Enhancement Models 6.5分前50% 73. Stereophonic Acoustic Echo Cancellation Using an Improved Af 6.0分前50% 74. Towards Real-Time Generative Speech Restoration with Flow-Ma 6.0分前50% 75. Is Phase Really Needed for Weakly-Supervised Dereverberation 6.0分前50% 📋 论文详情 🥇 A Lightweight Fourier-Based Network for Binaural Speech Enhancement with Spatial Cue Preservation 🔥 8.5/10 | 前25% | #语音增强 | #深度学习 | #轻量级模型 #空间音频 ...

ICASSP 2026 - 语音大模型论文列表

ICASSP 2026 - 语音大模型共 3 篇论文 ← 返回 ICASSP 2026 总览排名论文评分分档 🥇 Cross-Lingual Interleaving for Speech Language Models 7.5分前25% 🥈 Cross-Modal Knowledge Distillation for Speech Large Language 7.0分前25% 🥉 SpeechMapper: Speech-To-Text Embedding Projector for LLMs 7.0分前25% 📋 论文详情 🥇 Cross-Lingual Interleaving for Speech Language Models ✅ 7.5/10 | 前25% | #语音大模型 | #预训练 #多语言 | #预训练 #多语言 👥 作者与机构第一作者：Adel Moumen（Department of Engineering, University of Cambridge, UK）通讯作者：未说明作者列表：Adel Moumen（Department of Engineering, University of Cambridge, UK）、Guangzhi Sun（Department of Engineering, University of Cambridge, UK）、Philip C. Woodland（Department of Engineering, University of Cambridge, UK） 💡 毒舌点评 ...

ICASSP 2026 - 语音对话系统论文列表

ICASSP 2026 - 语音对话系统共 10 篇论文 ← 返回 ICASSP 2026 总览排名论文评分分档 🥇 DOMA: Leveraging Diffusion Language Models with Adaptive Pri 8.5分前25% 🥈 PersonaPlex: Voice and Role Control for Full Duplex Conversa 8.5分前25% 🥉 UTI-LLM: A Personalized Articulatory-Speech Therapy Assistan 7.5分前25% 4. A Dataset of Robot-Patient and Doctor-Patient Medical Dialog 7.5分前25% 5. Game-Time: Evaluating Temporal Dynamics in Spoken Language M 7.5分前25% 6. The Role of Prosodic and Lexical Cues in Turn-Taking with Se 7.5分前25% 7. Vocalnet-M2: Advancing Low-Latency Spoken Language Modeling 7.5分前25% 8. Easy Turn: Integrating Acoustic and Linguistic Modalities fo 7.0分前25% 9. Still Thinking or Stopped Talking? Dialogue Silence Intentio 6.5分前25% 10. Enhancing Dialogue-Related Speech Tasks with Generated Spoke 6.5分前25% 📋 论文详情 🥇 DOMA: Leveraging Diffusion Language Models with Adaptive Prior for Intent Classification and Slot Filling 🔥 8.5/10 | 前25% | #语音对话系统 | #扩散模型 | #意图识别 #槽填充 ...

ICASSP 2026 - 语音情感识别论文列表

ICASSP 2026 - 语音情感识别共 49 篇论文 ← 返回 ICASSP 2026 总览排名论文评分分档 🥇 Context-Aware Dynamic Graph Learning for Multimodal Emotion 8.8分前10% 🥈 Prompt-Guided Mixture-of-Experts for Robust Multimodal Senti 8.5分前25% 🥉 Clue2Emo: A Brain-Inspired Framework for Open-Vocabulary Mul 8.5分前25% 4. Attention-Weighted Centered Kernel Alignment for Knowledge D 8.0分前25% 5. Staged Diffusion with Hybrid Mixture-of-Experts (MOE) for Mu 8.0分前25% 6. DGSDNet: Dual-Graph Spectral Diffusion Network for Incomplet 8.0分前25% 7. Graph-based Modality Alignment for Robustness in Conversatio 8.0分前25% 8. Multimodal Self-Attention Network with Temporal Alignment fo 8.0分前25% 9. It Is Personal: The Importance of Personalization for Recogn 8.0分前25% 10. AMBER2: Dual Ambiguity-Aware Emotion Recognition Applied to 8.0分前25% 11. MI-Fuse: Label Fusion for Unsupervised Domain Adaptation wit 8.0分前25% 12. Speech Emotion Recognition based on Hierarchical Transformer 8.0分前25% 13. Affect-Jigsaw: Integrating Core and Peripheral Emotions for 8.0分前25% 14. When Audio Matters: A Lightweight, Hierarchical Fusion Model 8.0分前25% 15. Behind the Scenes: Mechanistic Interpretability of Lora-Adap 7.5分前25% 16. Encoding Emotion Through Self-Supervised Eye Movement Recons 7.5分前25% 17. Inter-Dialog Contrastive Learning for Multimodal Emotion Rec 7.5分前25% 18. ADH-VA: Adaptive Directed-Hypergraph Convolution with VA Con 7.5分前10% 19. SURE: Synergistic Uncertainty-Aware Reasoning for Multimodal 7.5分前25% 20. Tpeformer: Temporal Patch Embedding Transformer 7.5分前25% 21. LETPAV: Lexicon-Enhanced Text with Progressive Audio-Visual 7.5分前25% 22. Multimodal Variational Graph Network for Multimodal Sentimen 7.5分前25% 23. Diffemotalk: Audio-Driven Facial Animation with Fine-Grained 7.5分前25% 24. MECap-R1: Emotion-Aware Policy with Reinforcement Learning f 7.5分前25% 25. FIDIC:Fine-Grained Conversational Emotion Recognition via In 7.5分前25% 26. Whisper-QF: Leveraging Dual Cross-Attention Q-Former for Spe 7.5分前25% 27. Temporal Graph Modeling for Speech Emotion Recognition Using 7.5分前25% 28. Mixture-of-Experts Based Soft-Label Learning for Multi-Label 7.5分前25% 29. Multi-Channel Speech Enhancement for Cocktail Party Speech E 7.5分前25% 30. Evaluating Emotion Recognition in Spoken Language Models on 7.5分前50% 31. InconVAD: A Two-Stage Dual-Tower Framework for Multimodal Em 7.5分前25% 32. MSF-SER: Enriching Acoustic Modeling with Multi-Granularity 7.5分前25% 33. Rationale-Guided Learning for Multimodal Emotion Recognition 7.0分前25% 34. Bimodal Fusion Framework for Dynamic Facial Expression Recog 7.0分前25% 35. Stress Prediction from Temporal Emotion Trajectories in Clin 7.0分前25% 36. Emo-TTA: Improving Test-Time Adaptation of Audio-Language Mo 7.0分前25% 37. Test Time Adaptation for Speech Emotion Recognition 7.0分前25% 38. Plug-and-Play Emotion Graphs for Compositional Prompting in 7.0分前25% 39. Reasoning Driven Captions to Assist Noise Robust Speech Emot 7.0分前25% 40. EmoTri-RL: Emotion- and Cause-Aware Reinforcement Learning f 7.0分前25% 41. Modeling Both Intra- And Inter-Utterance Variability for Con 6.5分前25% 42. DDSR-Net: Robust Multimodal Sentiment Analysis via Dynamic M 6.5分前50% 43. Scaling Ambiguity: Augmenting Human Annotation in Speech Emo 6.5分前50% 44. Recovering Performance in Speech Emotion Recognition from Di 6.5分前50% 45. B-GRPO: Unsupervised Speech Emotion Recognition Based on Bat 6.5分前50% 46. Leveraging Large Speech Language Models as Evaluators for Ex 6.5分前50% 47. Gen-SER: When the Generative Model Meets Speech Emotion Reco 6.5分前50% 48. SmoothCLAP: Soft-Target Enhanced Contrastive Language-Audio 6.5分前50% 49. Acoustic and Facial Markers of Perceived Conversational Succ 6.0分前50% 📋 论文详情 🥇 Context-Aware Dynamic Graph Learning for Multimodal Emotion Recognition with Missing Modalities 🔥 8.8/10 | 前10% | #语音情感识别 | #多模态模型 | #大语言模型 #多任务学习 ...