@inproceedings{prasad-jyothi-2020-accents,
title = "How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems",
author = "Prasad, Archiki and
Jyothi, Preethi",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.345/",
doi = "10.18653/v1/2020.acl-main.345",
pages = "3739--3753",
abstract = "In this work, we present a detailed analysis of how accent information is reflected in the internal representation of speech in an end-to-end automatic speech recognition (ASR) system. We use a state-of-the-art end-to-end ASR system, comprising convolutional and recurrent layers, that is trained on a large amount of US-accented English speech and evaluate the model on speech samples from seven different English accents. We examine the effects of accent on the internal representation using three main probing techniques: a) Gradient-based explanation methods, b) Information-theoretic measures, and c) Outputs of accent and phone classifiers. We find different accents exhibiting similar trends irrespective of the probing technique used. We also find that most accent information is encoded within the first recurrent layer, which is suggestive of how one could adapt such an end-to-end model to learn representations that are invariant to accents."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prasad-jyothi-2020-accents">
<titleInfo>
<title>How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Archiki</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preethi</namePart>
<namePart type="family">Jyothi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</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>In this work, we present a detailed analysis of how accent information is reflected in the internal representation of speech in an end-to-end automatic speech recognition (ASR) system. We use a state-of-the-art end-to-end ASR system, comprising convolutional and recurrent layers, that is trained on a large amount of US-accented English speech and evaluate the model on speech samples from seven different English accents. We examine the effects of accent on the internal representation using three main probing techniques: a) Gradient-based explanation methods, b) Information-theoretic measures, and c) Outputs of accent and phone classifiers. We find different accents exhibiting similar trends irrespective of the probing technique used. We also find that most accent information is encoded within the first recurrent layer, which is suggestive of how one could adapt such an end-to-end model to learn representations that are invariant to accents.</abstract>
<identifier type="citekey">prasad-jyothi-2020-accents</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.345</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.345/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>3739</start>
<end>3753</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems
%A Prasad, Archiki
%A Jyothi, Preethi
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F prasad-jyothi-2020-accents
%X In this work, we present a detailed analysis of how accent information is reflected in the internal representation of speech in an end-to-end automatic speech recognition (ASR) system. We use a state-of-the-art end-to-end ASR system, comprising convolutional and recurrent layers, that is trained on a large amount of US-accented English speech and evaluate the model on speech samples from seven different English accents. We examine the effects of accent on the internal representation using three main probing techniques: a) Gradient-based explanation methods, b) Information-theoretic measures, and c) Outputs of accent and phone classifiers. We find different accents exhibiting similar trends irrespective of the probing technique used. We also find that most accent information is encoded within the first recurrent layer, which is suggestive of how one could adapt such an end-to-end model to learn representations that are invariant to accents.
%R 10.18653/v1/2020.acl-main.345
%U https://aclanthology.org/2020.acl-main.345/
%U https://doi.org/10.18653/v1/2020.acl-main.345
%P 3739-3753
Markdown (Informal)
[How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems](https://aclanthology.org/2020.acl-main.345/) (Prasad & Jyothi, ACL 2020)
ACL