面向任务的对话作为自监督自动语音识别的催化剂
Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition
AI总结：
针对ASR系统错误导致NLU应用失败且助手无法离线学习的问题，提出自监督对比微调方法CLC，利用不成功对话中的伪影改进模型，在公开元数据集OD3和真实系统中分别实现最高19.2%和6.7%的性能提升。
摘要：
尽管自动语音识别（ASR）系统的词错率持续下降，但构建于ASR系统之上的自然语言理解（NLU）应用仍将大量失败归因于低质量的语音识别结果。现有的助手系统收集了大量这些不成功的交互，但这些系统通常无法从这些交互中学习，即使是离线方式也不行。在这项工作中，我们引入了CLC：对话的对比学习，这是一系列以自监督方式对模型进行对比微调的方法，利用了与助手的不成功对话中容易检测到的伪影。我们证明，我们的CLC系列方法可以在OD3上提高ASR模型的性能，OD3是一个新的公开的大规模半合成音频任务导向对话元数据集，提升高达19.2%。这些增益也转移到现实世界系统中，我们表明CLC可以帮助在基线上提高高达6.7%的性能。我们在https://github.com/amazon-science/amazon-od3公开发布OD3。
英文摘要：
While word error rates of automatic speech recognition (ASR) systems have consistently fallen, natural language understanding (NLU) applications built on top of ASR systems still attribute significant numbers of failures to low-quality speech recognition results. Existing assistant systems collect large numbers of these unsuccessful interactions, but these systems usually fail to learn from these interactions, even in an offline fashion. In this work, we introduce CLC: Contrastive Learning for Conversations, a family of methods for contrastive fine-tuning of models in a self-supervised fashion, making use of easily detectable artifacts in unsuccessful conversations with assistants. We demonstrate that our CLC family of approaches can improve the performance of ASR models on OD3, a new public large-scale semi-synthetic meta-dataset of audio task-oriented dialogues, by up to 19.2%. These gains transfer to real-world systems as well, where we show that CLC can help to improve performance by up to 6.7% over baselines. We make OD3 publicly available at https://github.com/amazon-science/amazon-od3 .
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。
