通过延迟知识蒸馏提升流式语音识别准确率与响应速度
Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR
- 用延迟对齐缓冲区让流式模型模仿非流式教师模型的输出
- 40毫秒延迟下中文数据集CER低至5.42%，媲美320毫秒模型
- 适合追求低延迟高准确率的实时语音识别系统
基于CTC的流式语音识别在实际应用中备受关注，但面临小块输入时准确率下降和词元发出延迟的问题。为此，本文提出延迟知识蒸馏（Delayed-KD），将非流式教师模型的CTC后验概率应用于流式学生模型。具体而言，在极小块尺寸下引入时间对齐缓冲区（TAB），定义相对于非流式教师模型的相对延迟范围，以对齐CTC输出并减少非空白词元错配。此外，TAB实现对词元发出延迟的精细控制。在178小时AISHELL-1和1万小时WenetSpeech普通话数据集上的实验表明，Delayed-KD表现持续优异。令人印象深刻的是，延迟仅40毫秒时，AISHELL-1上的字符错误率（CER）降至5.42%，与运行于320毫秒延迟的先进模型U2++相当。
原文摘要 · Abstract (English)
CTC-based streaming ASR has gained significant attention in real-world applications but faces two main challenges: accuracy degradation in small chunks and token emission latency. To mitigate these challenges, we propose Delayed-KD, which applies delayed knowledge distillation on CTC posterior probabilities from a non-streaming to a streaming model. Specifically, with a tiny chunk size, we introduce a Temporal Alignment Buffer (TAB) that defines a relative delay range compared to the non-streaming teacher model to align CTC outputs and mitigate non-blank token mismatches. Additionally, TAB enables fine-grained control over token emission delay. Experiments on 178-hour AISHELL-1 and 10,000-hour WenetSpeech Mandarin datasets show consistent superiority of Delayed-KD. Impressively, Delayed-KD at 40 ms latency achieves a lower character error rate (CER) of 5.42% on AISHELL-1, comparable to the competitive U2++ model running at 320 ms latency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。