混合专家 on 语音/音频论文速递 https://nanless.github.io/audio-paper-digest-blog/tags/%E6%B7%B7%E5%90%88%E4%B8%93%E5%AE%B6/ Recent content in 混合专家 on 语音/音频论文速递 Hugo zh-cn Wed, 29 Apr 2026 00:00:00 +0000 Adaptive Task-Incremental Learning For Underwater Acoustic Recognition Based on Mixture-of-Experts Adapter https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-adaptive-task-incremental-learning-for-underwater/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-adaptive-task-incremental-learning-for-underwater/ 水下声学目标识别 | 7.0/10 Dual-Perspective Multimodal Sentiment Analysis with MoE Fusion: Representation Learning via Semantic Resonance and Divergence https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-dual-perspective-multimodal-sentiment-analysis/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-dual-perspective-multimodal-sentiment-analysis/ 多模态情感分析 | 7.0/10 Improving Multimodal Brain Encoding Model with Dynamic Subject-Awareness Routing https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-improving-multimodal-brain-encoding-model-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-improving-multimodal-brain-encoding-model-with/ 脑信号编码 | 8.0/10 Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence 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 Selective Hub Fusion with Modality-Heterogeneous Experts for Multimodal Emotion Recognition https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-selective-hub-fusion-with-modality-heterogeneous/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-selective-hub-fusion-with-modality-heterogeneous/ 多模态模型 | 6.5/10 SURE: Synergistic Uncertainty-Aware Reasoning for Multimodal Emotion Recognition in Conversations https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sure-synergistic-uncertainty-aware-reasoning-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sure-synergistic-uncertainty-aware-reasoning-for/ 语音情感识别 | 7.5/10 SwitchCodec: Adaptive Residual-Expert Sparse Quantization for High-Fidelity Neural Audio Coding 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 MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-move-translating-laughter-and-tears-via-mixture/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-move-translating-laughter-and-tears-via-mixture/ 这篇论文旨在解决语音到语音翻译（S2ST）系统普遍丢失源语音中非语言声音（如笑声、哭声）和情感信息的问题，这严重影响了跨语言交流的自然度和准确性。为此，作者提出了三项核心贡献：首先，设计了一个可扩展的自动化数据合成管道，用于生成大规模、高质量的英中富有表现力S2ST平行语料，克服了训练数据稀缺的瓶颈