面向多人对话语音识别的自说话人自适应说话人靶向方法
Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR
AI总结：
本研究提出一种无需显式说话人查询的流式多人对话ASR自说话人自适应方法，通过注入说话人专属内核实现即时适配，在离线和流式场景均达SOTA，可有效处理严重语音重叠问题。
摘要：
我们提出一种用于流式多人对话自动语音识别（ASR）的自说话人自适应方法，该方法无需显式的说话人查询。与需要目标说话人嵌入或注册音频的传统方法不同，我们的技术通过逐说话人语音活动预测，动态适配各个ASR实例。其核心创新在于，将通过说话人监督激活生成的说话人专属内核，注入选定的ASR编码器层。这使得模型能够即时适配目标说话人，即便在流式场景下也能处理完全重叠的语音。实验表明，该方法在离线和流式场景下均达到了当前最优性能，证明我们的自适应方法通过精简的聚焦说话人识别，有效应对了严重的语音重叠问题。研究结果验证了所提出的自说话人自适应方法，是严重重叠语音场景下多人对话ASR的稳健解决方案。
英文摘要：
We propose a self-speaker adaptation method for streaming multi-talker automatic speech recognition (ASR) that eliminates the need for explicit speaker queries. Unlike conventional approaches requiring target speaker embeddings or enrollment audio, our technique dynamically adapts individual ASR instances through speaker-wise speech activity prediction. The key innovation involves injecting speaker-specific kernels generated via speaker supervision activations into selected ASR encoder layers. This enables instantaneous speaker adaptation to target speakers while handling fully overlapped speech even in a streaming scenario. Experiments show state-of-the-art performance in both offline and streaming scenarios, demonstrating that our self-adaptive method effectively addresses severe speech overlap through streamlined speaker-focused recognition. The results validate the proposed self-speaker adaptation approach as a robust solution for multi-talker ASR under severe overlapping speech conditions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
