改进端到端流式ASR中对话语音的端点检测
Improving endpoint detection in end-to-end streaming ASR for conversational speech
AI总结：
针对端到端流式ASR中端点检测因输出延迟导致错误的问题，提出引入词尾标记与延迟惩罚，并利用辅助网络进行帧级语音活动检测，在Switchboard语料上验证了改进效果。
摘要：
ASR端点检测（EP）在支持人类或人工智能体进行人机/人人对话的产品中，对提供良好用户体验起着重要作用。基于转换器的ASR（T-ASR）是一种适用于流式处理的端到端（E2E）ASR建模技术。T-ASR的一个主要局限性是ASR输出的延迟发射，这可能导致端点检测中的错误或延迟。不准确的端点检测会在用户说话时切断用户，返回不完整的转录文本，而端点检测的延迟则会增加感知延迟，降低用户体验。我们提出了通过解决延迟发射以及端点检测错误来改进端点检测的方法。为了解决延迟发射问题，我们在每个单词的末尾引入一个词尾标记，并附带延迟惩罚。端点检测延迟通过使用辅助网络获得可靠的帧级语音活动检测来解决。我们在Switchboard对话语音语料库上应用了所提出的方法，并与延迟惩罚方法进行了评估对比。
英文摘要：
ASR endpointing (EP) plays a major role in delivering a good user experience in products supporting human or artificial agents in human-human/machine conversations. Transducer-based ASR (T-ASR) is an end-to-end (E2E) ASR modelling technique preferred for streaming. A major limitation of T-ASR is delayed emission of ASR outputs, which could lead to errors or delays in EP. Inaccurate EP will cut the user off while speaking, returning incomplete transcript while delays in EP will increase the perceived latency, degrading the user experience. We propose methods to improve EP by addressing delayed emission along with EP mistakes. To address the delayed emission problem, we introduce an end-of-word token at the end of each word, along with a delay penalty. The EP delay is addressed by obtaining a reliable frame-level speech activity detection using an auxiliary network. We apply the proposed methods on Switchboard conversational speech corpus and evaluate it against a delay penalty method.
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。
