Disfluency detection is usually an intermediate step between an automatic speech recognition (ASR) system and a downstream task. By contrast, this paper aims to investigate the task of end-to-end speech recognition and disfluency removal. We specifically explore whether it is possible to train an ASR model to directly map disfluent speech into fluent transcripts, without relying on a separate disfluency detection model. We show that end-to-end models do learn to directly generate fluent transcripts; however, their performance is slightly worse than a baseline pipeline approach consisting of an ASR system and a disfluency detection model. We also propose two new metrics that can be used for evaluating integrated ASR and disfluency models. The findings of this paper can serve as a benchmark for further research on the task of end-to-end speech recognition and disfluency removal in the future.

中文翻译：

---

端到端语音识别和不流利消除

不流畅检测通常是自动语音识别 (ASR) 系统和下游任务之间的中间步骤。相比之下，本文旨在研究端到端语音识别和不流畅消除的任务。我们专门探讨是否可以训练 ASR 模型将不流利的语音直接映射到流利的成绩单，而无需依赖单独的不流利检测模型。我们表明端到端模型确实学会了直接生成流畅的成绩单；然而，它们的性能比由 ASR 系统和不流畅检测模型组成的基线管道方法略差。我们还提出了两个可用于评估集成 ASR 和不流畅模型的新指标。