https://nanless.github.io/audio-paper-digest-blog/tags/%E9%9F%B3%E8%A7%86%E9%A2%91/ Recent content in 音视频 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-aishell6-whisper-a-chinese-mandarin-audio-visual/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-aishell6-whisper-a-chinese-mandarin-audio-visual/ 语音识别 | 8.3/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-an-audio-visual-speech-separation-network-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-an-audio-visual-speech-separation-network-with/ 语音分离 | 7.5/10 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-asynchrony-aware-decoupled-multimodal-control-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-asynchrony-aware-decoupled-multimodal-control-for/ 语音合成 | 7.5/10 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-audio-visual-feature-fusion-for-calibrating/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-audio-visual-feature-fusion-for-calibrating/ 视频片段检索 | 7.0/10 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-bimodal-fusion-framework-for-dynamic-facial/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-bimodal-fusion-framework-for-dynamic-facial/ 语音情感识别 | 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-cova-text-guided-composed-video-retrieval-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cova-text-guided-composed-video-retrieval-for/ 跨模态检索 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cross-modal-bottleneck-fusion-for-noise-robust/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-cross-modal-bottleneck-fusion-for-noise-robust/ 语音识别 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-depthtalk-few-shot-talking-head-generation-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-depthtalk-few-shot-talking-head-generation-with/ 说话人生成 | 7.0/10 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-fastav-efficient-token-pruning-for-audio-visual/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-fastav-efficient-token-pruning-for-audio-visual/ 音频问答 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-foleybench-a-benchmark-for-video-to-audio-models/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-foleybench-a-benchmark-for-video-to-audio-models/ 音频生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-gms-cavp-improving-audio-video-correspondence/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-gms-cavp-improving-audio-video-correspondence/ 音频生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/icassp2026-task-112/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/icassp2026-task-112/ 共 6 篇 ICASSP 2026 音视频 方向论文 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-meanflow-accelerated-multimodal-video-to-audio/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-meanflow-accelerated-multimodal-video-to-audio/ 音频生成 | 7.5/10 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 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-motionbeat-motion-aligned-music-representation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-motionbeat-motion-aligned-music-representation/ 舞蹈生成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-msct-differential-cross-modal-attention-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-msct-differential-cross-modal-attention-for/ 音频深度伪造检测 | 6.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-multimodal-self-attention-network-with-temporal/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-multimodal-self-attention-network-with-temporal/ 语音情感识别 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-noise-robust-av-asr-using-visual-features-both-in/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-noise-robust-av-asr-using-visual-features-both-in/ 语音识别 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-omni-avsr-towards-unified-multimodal-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-omni-avsr-towards-unified-multimodal-speech/ 语音识别 | 8.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-performsinger-multimodal-singing-voice-synthesis/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-performsinger-multimodal-singing-voice-synthesis/ 歌唱语音合成 | 4.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-prototype-guided-cross-modal-contrastive-learning/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-prototype-guided-cross-modal-contrastive-learning/ 语音分离 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-pstalker-realistic-3d-talking-head-synthesis-via/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-pstalker-realistic-3d-talking-head-synthesis-via/ 说话人合成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-purification-before-fusion-toward-mask-free/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-purification-before-fusion-toward-mask-free/ 语音识别 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-rap-real-time-audio-driven-portrait-animation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-rap-real-time-audio-driven-portrait-animation/ 音视频 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-rethinking-entity-disambiguation-in-complex/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-rethinking-entity-disambiguation-in-complex/ 实体消歧 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-semantic-guided-pseudo-feature-attention-network/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-semantic-guided-pseudo-feature-attention-network/ 音频分类 零样本学习 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sightsound-r1-cross-modal-reasoning-distillation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sightsound-r1-cross-modal-reasoning-distillation/ 音频问答 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-siren-spatially-informed-reconstruction-of/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-siren-spatially-informed-reconstruction-of/ 空间音频 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sounding-highlights-dual-pathway-audio-encoders/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sounding-highlights-dual-pathway-audio-encoders/ 视频高光检测 | 8.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sparse-view-visual-acoustic-latent-learning-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sparse-view-visual-acoustic-latent-learning-for/ 空间音频 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-spiking-temporal-enhanced-network-for-zero-shot/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-spiking-temporal-enhanced-network-for-zero-shot/ 音频分类 | 7.0/10 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-teacher-guided-pseudo-supervision-and-cross-modal/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-teacher-guided-pseudo-supervision-and-cross-modal/ 音视频 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-temporal-spatial-decouple-before-act-disentangled/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-temporal-spatial-decouple-before-act-disentangled/ 情感分析 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-the-synergistic-role-of-audio-and-large-video/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-the-synergistic-role-of-audio-and-large-video/ 领域适应 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-training-free-multimodal-guidance-for-video-to/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-training-free-multimodal-guidance-for-video-to/ 音频生成 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-uncertainty-aware-3d-emotional-talking-face/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-uncertainty-aware-3d-emotional-talking-face/ 音视频 | 8.0/10 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-vividtalker-a-modular-framework-for-expressive-3d/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-vividtalker-a-modular-framework-for-expressive-3d/ 语音合成 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-avsdnet-a-novel-end-to-end-neural-network/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-avsdnet-a-novel-end-to-end-neural-network/ 说话人分离 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-hallo-live-real-time-streaming-joint-audio-video/ Tue, 28 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-hallo-live-real-time-streaming-joint-audio-video/ 音视频 | 8.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-talker-t2av-joint-talking-audio-video-generation/ Tue, 28 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-28-talker-t2av-joint-talking-audio-video-generation/ 语音合成 | 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/2026-04-24-misinformation-span-detection-in-videos-via-audio/ Fri, 24 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-misinformation-span-detection-in-videos-via-audio/ 音频安全 | 7.5/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-video-robin-autoregressive-diffusion-planning-for/ Fri, 24 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-video-robin-autoregressive-diffusion-planning-for/ 音乐生成 | 7.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-aprvos-1st-place-winner-of-5th-pvuw-mevis-audio/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-aprvos-1st-place-winner-of-5th-pvuw-mevis-audio/ 这篇论文报告了APRVOS系统，一个专为MEVIS_Audio（音频条件下的指代视频对象分割）任务设计的冠军方案。**要解决的问题**是传统文本指代分割模型无法直接处理包含噪声、不完整且可能描述视频中不存在物体的语音输入。**采用的方法**是一个四阶段流水线：首先使用VibeVoice-ASR将语音 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-uaf-a-unified-audio-front-end-llm-for-full-duplex/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-uaf-a-unified-audio-front-end-llm-for-full-duplex/ **核心贡献**：本文提出了首个专为全双工语音交互设计的统一音频前端大模型（UAF）。它打破了传统级联式前端处理的范式，将语音活动检测（VAD）、说话人识别（SR）、自动语音识别（ASR）、轮次检测（TD）和问答（QA）等多个任务，统一建模为一个自回归序列预测问题。 **关键方法**：模型采用“音 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-avrt-audio-visual-reasoning-transfer-through/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-avrt-audio-visual-reasoning-transfer-through/ 本文旨在解决多模态大模型在音视频联合推理任务上缺乏高质量训练数据的核心挑战。**核心贡献**是提出了AVRT框架，通过组合单模态专家模型的能力来合成多模态推理数据。**关键方法**分为两步：1）**数据生成**：使用专门的视觉教师（Kimi-VL-Thinking）和音频教师（Audio Flami https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-video-robin-autoregressive-diffusion-planning-for/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-video-robin-autoregressive-diffusion-planning-for/ 本文针对现有视频到音乐（V2M）生成模型缺乏对创作者风格、主题等细粒度意图控制的问题，提出了Video-Robin，一个结合文本提示的视频配乐框架。其核心方法是将生成过程解耦为两个阶段：首先，一个多模态自回归规划头（AR-Head）整合视频帧和文本提示，通过语义语言模型、有限标量量化（FSQ）和残差 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-beyond-monologue-interactive-talking-listening/ Mon, 20 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-beyond-monologue-interactive-talking-listening/ 本文旨在解决从单向“独白”式虚拟人生成迈向自然“全双工”交互式生成的核心挑战。**核心问题**在于，现有方法要么因严格的帧对齐而反应僵硬，要么因引入全局注意力而破坏唇同步。**关键方法**是提出一个基于多头高斯核（MHGK）的统一注意力架构，该机制通过为不同的注意力头分配从窄到宽的高斯分布感受野，使 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-generalizable-audio-visual-navigation-via/ Mon, 20 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-generalizable-audio-visual-navigation-via/ 本文旨在解决音频-视觉导航（AVN）智能体在未见环境和未闻声音类别下泛化能力差的核心问题。作者指出，现有方法性能下降主要源于两个因素：一是音频表征混淆了语义与空间信息，导致对未闻声��定位不准；二是强化学习策略过拟合于训练环境的动态和布局。为此，本文提出了一个名为BDATP的即插即用框架。在感知层面 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-ps-tts-phonetic-synchronization-in-text-to-speech/ Mon, 20 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-ps-tts-phonetic-synchronization-in-text-to-speech/ 这篇论文旨在解决自动配音（AD）中目标语音与源语音在时长和唇形上的同步难题。其核心贡献是提出了一套两阶段的文本改写方法，并集成到TTS系统中：首先通过语言模型进行**等时性**改写，确保目标语音时长匹配源语音；其次引入**音素同步（PS）**，使用动态时间规整（DTW）和从训练数据中学习的元音距离， https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-avid-a-benchmark-for-omni-modal-audio-visual/ Sun, 19 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-avid-a-benchmark-for-omni-modal-audio-visual/ 这篇论文旨在解决当前全模态大模型在音视频不一致性理解能力上缺乏系统性评估的问题。现有基准要么只关注音视频对齐事件，要么局限于检测深度伪造中的低级伪影，无法评估模型对长视频中语义级矛盾的理解。为此，作者 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-listening-deepfake-detection-a-new-perspective/ Sun, 19 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-listening-deepfake-detection-a-new-perspective/ 本文首次提出了“聆听深度伪造检测”这一新任务，旨在识别视频中人物在倾听状态下（非说话时）的伪造反应，弥补了现有研究主要集中于“说话”场景的不足。为解决此任务数据稀缺的问题，作者构建了首个专门数据集Li https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-tora3-trajectory-guided-audio-video-generation/ Sun, 19 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-19-tora3-trajectory-guided-audio-video-generation/ 本文针对现有音视频（AV）生成模型中存在的运动不真实、声音与运动事件不同步、声音强度与运动强度不匹配等问题，提出了Tora3框架。其核心创新在于**将物体轨迹视为连接视觉与听觉模态的共享运动学先验**