当前位置:
X-MOL 学术
›
arXiv.cs.LG
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
End-to-End Speech Recognition and Disfluency Removal
arXiv - CS - Machine Learning Pub Date : 2020-09-22 , DOI: arxiv-2009.10298 Paria Jamshid Lou and Mark Johnson
arXiv - CS - Machine Learning Pub Date : 2020-09-22 , DOI: arxiv-2009.10298 Paria Jamshid Lou and Mark Johnson
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。
更新日期:2020-09-30
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。