https://nanless.github.io/audio-paper-digest-blog/tags/%E5%8F%AF%E8%A7%A3%E9%87%8A%E6%80%A7/ Recent content in 可解释性 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-connecting-layer-wise-representation-of-wavlm/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-connecting-layer-wise-representation-of-wavlm/ 说话人验证 | 6.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-gloria-gated-low-rank-interpretable-adaptation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-gloria-gated-low-rank-interpretable-adaptation/ 语音识别 | 8.0/10 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-iclad-in-context-learning-with-comparison/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-iclad-in-context-learning-with-comparison/ 本文针对音频深度伪造检测模型在真实场景（in-the-wild）中泛化能力差的核心问题，提出了一种名为ICLAD的全新范式。该框架利用音频语言模型（ALM）的上下文学习能力，实现了无需训练的快速适应。其核心是创新的**成对比较推理**策略：在离线阶段，引导ALM为每个样本同时生成“真实”和“伪造”的 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21/ 共分析 34 篇语音/AI 论文