https://nanless.github.io/audio-paper-digest-blog/tags/%E8%AF%AD%E9%9F%B3%E8%AF%86%E5%88%AB%E6%B5%81%E5%BC%8F%E5%A4%84%E7%90%86%E4%B8%80%E8%87%B4%E6%80%A7%E6%AD%A3%E5%88%99%E5%8C%96%E7%BB%9F%E4%B8%80%E9%9F%B3%E9%A2%91%E6%A8%A1%E5%9E%8B%E5%BC%80%E6%BA%90%E5%B7%A5%E5%85%B7/ Recent content in 语音识别，流式处理，一致性正则化，统一音频模型，开源工具 on 语音/音频论文速递 Hugo zh-cn Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-reducing-the-offline-streaming-gap-for-unified/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-reducing-the-offline-streaming-gap-for-unified/ 本文旨在解决训练单一自动语音识别（ASR）模型同时高效支持高精度离线转写和低延迟流式识别这一挑战。现有统一模型在低延迟流式模式下性能下降明显。作者提出了一个统一的RNN-Transducer (RNNT) 框架，其核心是结合了**带右上下文的chunk限制注意力**和**动态chunk卷积（DCCo