@inproceedings{masson-carson-berndsen-2023-investigating,
title = "Investigating Phoneme Similarity with Artificially Accented Speech",
author = "Masson, Margot and
Carson-berndsen, Julie",
editor = {Nicolai, Garrett and
Chodroff, Eleanor and
Mailhot, Frederic and
{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
booktitle = "Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.sigmorphon-1.6",
doi = "10.18653/v1/2023.sigmorphon-1.6",
pages = "49--57",
abstract = "While the deep learning revolution has led to significant performance improvements in speech recognition, accented speech remains a challenge. Current approaches to this challenge typically do not seek to understand and provide explanations for the variations of accented speech, whether they stem from native regional variation or non-native error patterns. This paper seeks to address non-native speaker variations from both a knowledge-based and a data-driven perspective. We propose to approximate non-native accented-speech pronunciation patterns by the means of two approaches: based on phonetic and phonological knowledge on the one hand and inferred from a text-to-speech system on the other. Artificial speech is then generated with a range of variants which have been captured in confusion matrices representing phoneme similarities. We then show that non-native accent confusions actually propagate to the transcription from the ASR, thus suggesting that the inference of accent specific phoneme confusions is achievable from artificial speech.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="masson-carson-berndsen-2023-investigating">
<titleInfo>
<title>Investigating Phoneme Similarity with Artificially Accented Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Margot</namePart>
<namePart type="family">Masson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julie</namePart>
<namePart type="family">Carson-berndsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Garrett</namePart>
<namePart type="family">Nicolai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleanor</namePart>
<namePart type="family">Chodroff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Mailhot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While the deep learning revolution has led to significant performance improvements in speech recognition, accented speech remains a challenge. Current approaches to this challenge typically do not seek to understand and provide explanations for the variations of accented speech, whether they stem from native regional variation or non-native error patterns. This paper seeks to address non-native speaker variations from both a knowledge-based and a data-driven perspective. We propose to approximate non-native accented-speech pronunciation patterns by the means of two approaches: based on phonetic and phonological knowledge on the one hand and inferred from a text-to-speech system on the other. Artificial speech is then generated with a range of variants which have been captured in confusion matrices representing phoneme similarities. We then show that non-native accent confusions actually propagate to the transcription from the ASR, thus suggesting that the inference of accent specific phoneme confusions is achievable from artificial speech.</abstract>
<identifier type="citekey">masson-carson-berndsen-2023-investigating</identifier>
<identifier type="doi">10.18653/v1/2023.sigmorphon-1.6</identifier>
<location>
<url>https://aclanthology.org/2023.sigmorphon-1.6</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>49</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating Phoneme Similarity with Artificially Accented Speech
%A Masson, Margot
%A Carson-berndsen, Julie
%Y Nicolai, Garrett
%Y Chodroff, Eleanor
%Y Mailhot, Frederic
%Y Çöltekin, Çağrı
%S Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F masson-carson-berndsen-2023-investigating
%X While the deep learning revolution has led to significant performance improvements in speech recognition, accented speech remains a challenge. Current approaches to this challenge typically do not seek to understand and provide explanations for the variations of accented speech, whether they stem from native regional variation or non-native error patterns. This paper seeks to address non-native speaker variations from both a knowledge-based and a data-driven perspective. We propose to approximate non-native accented-speech pronunciation patterns by the means of two approaches: based on phonetic and phonological knowledge on the one hand and inferred from a text-to-speech system on the other. Artificial speech is then generated with a range of variants which have been captured in confusion matrices representing phoneme similarities. We then show that non-native accent confusions actually propagate to the transcription from the ASR, thus suggesting that the inference of accent specific phoneme confusions is achievable from artificial speech.
%R 10.18653/v1/2023.sigmorphon-1.6
%U https://aclanthology.org/2023.sigmorphon-1.6
%U https://doi.org/10.18653/v1/2023.sigmorphon-1.6
%P 49-57
Markdown (Informal)
[Investigating Phoneme Similarity with Artificially Accented Speech](https://aclanthology.org/2023.sigmorphon-1.6) (Masson & Carson-berndsen, SIGMORPHON 2023)
ACL