@inproceedings{park-etal-2021-bts,
title = "{BTS}: Back {T}ran{S}cription for Speech-to-Text Post-Processor using Text-to-Speech-to-Text",
author = "Park, Chanjun and
Seo, Jaehyung and
Lee, Seolhwa and
Lee, Chanhee and
Moon, Hyeonseok and
Eo, Sugyeong and
Lim, Heuiseok",
editor = "Nakazawa, Toshiaki and
Nakayama, Hideki and
Goto, Isao and
Mino, Hideya and
Ding, Chenchen and
Dabre, Raj and
Kunchukuttan, Anoop and
Higashiyama, Shohei and
Manabe, Hiroshi and
Pa, Win Pa and
Parida, Shantipriya and
Bojar, Ond{\v{r}}ej and
Chu, Chenhui and
Eriguchi, Akiko and
Abe, Kaori and
Oda, Yusuke and
Sudoh, Katsuhito and
Kurohashi, Sadao and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 8th Workshop on Asian Translation (WAT2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wat-1.10",
doi = "10.18653/v1/2021.wat-1.10",
pages = "106--116",
abstract = "With the growing popularity of smart speakers, such as Amazon Alexa, speech is becoming one of the most important modes of human-computer interaction. Automatic speech recognition (ASR) is arguably the most critical component of such systems, as errors in speech recognition propagate to the downstream components and drastically degrade the user experience. A simple and effective way to improve the speech recognition accuracy is to apply automatic post-processor to the recognition result. However, training a post-processor requires parallel corpora created by human annotators, which are expensive and not scalable. To alleviate this problem, we propose Back TranScription (BTS), a denoising-based method that can create such corpora without human labor. Using a raw corpus, BTS corrupts the text using Text-to-Speech (TTS) and Speech-to-Text (STT) systems. Then, a post-processing model can be trained to reconstruct the original text given the corrupted input. Quantitative and qualitative evaluations show that a post-processor trained using our approach is highly effective in fixing non-trivial speech recognition errors such as mishandling foreign words. We present the generated parallel corpus and post-processing platform to make our results publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2021-bts">
<titleInfo>
<title>BTS: Back TranScription for Speech-to-Text Post-Processor using Text-to-Speech-to-Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chanjun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaehyung</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seolhwa</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chanhee</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeonseok</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sugyeong</namePart>
<namePart type="family">Eo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heuiseok</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Asian Translation (WAT2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Nakayama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isao</namePart>
<namePart type="family">Goto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideya</namePart>
<namePart type="family">Mino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenchen</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shohei</namePart>
<namePart type="family">Higashiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroshi</namePart>
<namePart type="family">Manabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Win</namePart>
<namePart type="given">Pa</namePart>
<namePart type="family">Pa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shantipriya</namePart>
<namePart type="family">Parida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akiko</namePart>
<namePart type="family">Eriguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaori</namePart>
<namePart type="family">Abe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Oda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katsuhito</namePart>
<namePart type="family">Sudoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</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>With the growing popularity of smart speakers, such as Amazon Alexa, speech is becoming one of the most important modes of human-computer interaction. Automatic speech recognition (ASR) is arguably the most critical component of such systems, as errors in speech recognition propagate to the downstream components and drastically degrade the user experience. A simple and effective way to improve the speech recognition accuracy is to apply automatic post-processor to the recognition result. However, training a post-processor requires parallel corpora created by human annotators, which are expensive and not scalable. To alleviate this problem, we propose Back TranScription (BTS), a denoising-based method that can create such corpora without human labor. Using a raw corpus, BTS corrupts the text using Text-to-Speech (TTS) and Speech-to-Text (STT) systems. Then, a post-processing model can be trained to reconstruct the original text given the corrupted input. Quantitative and qualitative evaluations show that a post-processor trained using our approach is highly effective in fixing non-trivial speech recognition errors such as mishandling foreign words. We present the generated parallel corpus and post-processing platform to make our results publicly available.</abstract>
<identifier type="citekey">park-etal-2021-bts</identifier>
<identifier type="doi">10.18653/v1/2021.wat-1.10</identifier>
<location>
<url>https://aclanthology.org/2021.wat-1.10</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>106</start>
<end>116</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BTS: Back TranScription for Speech-to-Text Post-Processor using Text-to-Speech-to-Text
%A Park, Chanjun
%A Seo, Jaehyung
%A Lee, Seolhwa
%A Lee, Chanhee
%A Moon, Hyeonseok
%A Eo, Sugyeong
%A Lim, Heuiseok
%Y Nakazawa, Toshiaki
%Y Nakayama, Hideki
%Y Goto, Isao
%Y Mino, Hideya
%Y Ding, Chenchen
%Y Dabre, Raj
%Y Kunchukuttan, Anoop
%Y Higashiyama, Shohei
%Y Manabe, Hiroshi
%Y Pa, Win Pa
%Y Parida, Shantipriya
%Y Bojar, Ondřej
%Y Chu, Chenhui
%Y Eriguchi, Akiko
%Y Abe, Kaori
%Y Oda, Yusuke
%Y Sudoh, Katsuhito
%Y Kurohashi, Sadao
%Y Bhattacharyya, Pushpak
%S Proceedings of the 8th Workshop on Asian Translation (WAT2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F park-etal-2021-bts
%X With the growing popularity of smart speakers, such as Amazon Alexa, speech is becoming one of the most important modes of human-computer interaction. Automatic speech recognition (ASR) is arguably the most critical component of such systems, as errors in speech recognition propagate to the downstream components and drastically degrade the user experience. A simple and effective way to improve the speech recognition accuracy is to apply automatic post-processor to the recognition result. However, training a post-processor requires parallel corpora created by human annotators, which are expensive and not scalable. To alleviate this problem, we propose Back TranScription (BTS), a denoising-based method that can create such corpora without human labor. Using a raw corpus, BTS corrupts the text using Text-to-Speech (TTS) and Speech-to-Text (STT) systems. Then, a post-processing model can be trained to reconstruct the original text given the corrupted input. Quantitative and qualitative evaluations show that a post-processor trained using our approach is highly effective in fixing non-trivial speech recognition errors such as mishandling foreign words. We present the generated parallel corpus and post-processing platform to make our results publicly available.
%R 10.18653/v1/2021.wat-1.10
%U https://aclanthology.org/2021.wat-1.10
%U https://doi.org/10.18653/v1/2021.wat-1.10
%P 106-116
Markdown (Informal)
[BTS: Back TranScription for Speech-to-Text Post-Processor using Text-to-Speech-to-Text](https://aclanthology.org/2021.wat-1.10) (Park et al., WAT 2021)
ACL