End-to-End Speech Recognition and Disfluency Removal release_igk4kggpzvejpeihaojwj33ady

by Paria Jamshid Lou, Mark Johnson

Released as a article .

2020  

Abstract

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.
In text/plain format

Archived Files and Locations

application/pdf  415.0 kB
file_niinjznqxjczzgqvkhdy25cbxe
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-09-28
Version   v3
Language   en ?
arXiv  2009.10298v3
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 6f2c8ee7-0dbb-4c4b-9b4e-dddc09cafd3e
API URL: JSON