@inproceedings{jamshid-lou-johnson-2020-end,
title = "End-to-End Speech Recognition and Disfluency Removal",
author = "Jamshid Lou, Paria and
Johnson, Mark",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.186",
doi = "10.18653/v1/2020.findings-emnlp.186",
pages = "2051--2061",
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 specialized disfluency detection model. We also propose two new metrics for evaluating integrated ASR and disfluency removal 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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jamshid-lou-johnson-2020-end">
<titleInfo>
<title>End-to-End Speech Recognition and Disfluency Removal</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paria</namePart>
<namePart type="family">Jamshid Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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 specialized disfluency detection model. We also propose two new metrics for evaluating integrated ASR and disfluency removal 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.</abstract>
<identifier type="citekey">jamshid-lou-johnson-2020-end</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.186</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.186</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2051</start>
<end>2061</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T End-to-End Speech Recognition and Disfluency Removal
%A Jamshid Lou, Paria
%A Johnson, Mark
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F jamshid-lou-johnson-2020-end
%X 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 specialized disfluency detection model. We also propose two new metrics for evaluating integrated ASR and disfluency removal 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.
%R 10.18653/v1/2020.findings-emnlp.186
%U https://aclanthology.org/2020.findings-emnlp.186
%U https://doi.org/10.18653/v1/2020.findings-emnlp.186
%P 2051-2061
Markdown (Informal)
[End-to-End Speech Recognition and Disfluency Removal](https://aclanthology.org/2020.findings-emnlp.186) (Jamshid Lou & Johnson, Findings 2020)
ACL