@inproceedings{omachi-etal-2021-end,
title = "End-to-end {ASR} to jointly predict transcriptions and linguistic annotations",
author = "Omachi, Motoi and
Fujita, Yuya and
Watanabe, Shinji and
Wiesner, Matthew",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.149",
doi = "10.18653/v1/2021.naacl-main.149",
pages = "1861--1871",
abstract = "We propose a Transformer-based sequence-to-sequence model for automatic speech recognition (ASR) capable of simultaneously transcribing and annotating audio with linguistic information such as phonemic transcripts or part-of-speech (POS) tags. Since linguistic information is important in natural language processing (NLP), the proposed ASR is especially useful for speech interface applications, including spoken dialogue systems and speech translation, which combine ASR and NLP. To produce linguistic annotations, we train the ASR system using modified training targets: each grapheme or multi-grapheme unit in the target transcript is followed by an aligned phoneme sequence and/or POS tag. Since our method has access to the underlying audio data, we can estimate linguistic annotations more accurately than pipeline approaches in which NLP-based methods are applied to a hypothesized ASR transcript. Experimental results on Japanese and English datasets show that the proposed ASR system is capable of simultaneously producing high-quality transcriptions and linguistic annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="omachi-etal-2021-end">
<titleInfo>
<title>End-to-end ASR to jointly predict transcriptions and linguistic annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Motoi</namePart>
<namePart type="family">Omachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuya</namePart>
<namePart type="family">Fujita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinji</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Wiesner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>We propose a Transformer-based sequence-to-sequence model for automatic speech recognition (ASR) capable of simultaneously transcribing and annotating audio with linguistic information such as phonemic transcripts or part-of-speech (POS) tags. Since linguistic information is important in natural language processing (NLP), the proposed ASR is especially useful for speech interface applications, including spoken dialogue systems and speech translation, which combine ASR and NLP. To produce linguistic annotations, we train the ASR system using modified training targets: each grapheme or multi-grapheme unit in the target transcript is followed by an aligned phoneme sequence and/or POS tag. Since our method has access to the underlying audio data, we can estimate linguistic annotations more accurately than pipeline approaches in which NLP-based methods are applied to a hypothesized ASR transcript. Experimental results on Japanese and English datasets show that the proposed ASR system is capable of simultaneously producing high-quality transcriptions and linguistic annotations.</abstract>
<identifier type="citekey">omachi-etal-2021-end</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.149</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.149</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>1861</start>
<end>1871</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T End-to-end ASR to jointly predict transcriptions and linguistic annotations
%A Omachi, Motoi
%A Fujita, Yuya
%A Watanabe, Shinji
%A Wiesner, Matthew
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F omachi-etal-2021-end
%X We propose a Transformer-based sequence-to-sequence model for automatic speech recognition (ASR) capable of simultaneously transcribing and annotating audio with linguistic information such as phonemic transcripts or part-of-speech (POS) tags. Since linguistic information is important in natural language processing (NLP), the proposed ASR is especially useful for speech interface applications, including spoken dialogue systems and speech translation, which combine ASR and NLP. To produce linguistic annotations, we train the ASR system using modified training targets: each grapheme or multi-grapheme unit in the target transcript is followed by an aligned phoneme sequence and/or POS tag. Since our method has access to the underlying audio data, we can estimate linguistic annotations more accurately than pipeline approaches in which NLP-based methods are applied to a hypothesized ASR transcript. Experimental results on Japanese and English datasets show that the proposed ASR system is capable of simultaneously producing high-quality transcriptions and linguistic annotations.
%R 10.18653/v1/2021.naacl-main.149
%U https://aclanthology.org/2021.naacl-main.149
%U https://doi.org/10.18653/v1/2021.naacl-main.149
%P 1861-1871
Markdown (Informal)
[End-to-end ASR to jointly predict transcriptions and linguistic annotations](https://aclanthology.org/2021.naacl-main.149) (Omachi et al., NAACL 2021)
ACL