@inproceedings{mayn-etal-2021-familiar,
title = "Familiar words but strange voices: Modelling the influence of speech variability on word recognition",
author = "Mayn, Alexandra and
Abdullah, Badr M. and
Klakow, Dietrich",
editor = "Sorodoc, Ionut-Teodor and
Sushil, Madhumita and
Takmaz, Ece and
Agirre, Eneko",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-srw.14",
doi = "10.18653/v1/2021.eacl-srw.14",
pages = "96--102",
abstract = "We present a deep neural model of spoken word recognition which is trained to retrieve the meaning of a word (in the form of a word embedding) given its spoken form, a task which resembles that faced by a human listener. Furthermore, we investigate the influence of variability in speech signals on the model{'}s performance. To this end, we conduct of set of controlled experiments using word-aligned read speech data in German. Our experiments show that (1) the model is more sensitive to dialectical variation than gender variation, and (2) recognition performance of word cognates from related languages reflect the degree of relatedness between languages in our study. Our work highlights the feasibility of modeling human speech perception using deep neural networks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mayn-etal-2021-familiar">
<titleInfo>
<title>Familiar words but strange voices: Modelling the influence of speech variability on word recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Mayn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Abdullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ionut-Teodor</namePart>
<namePart type="family">Sorodoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madhumita</namePart>
<namePart type="family">Sushil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</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 present a deep neural model of spoken word recognition which is trained to retrieve the meaning of a word (in the form of a word embedding) given its spoken form, a task which resembles that faced by a human listener. Furthermore, we investigate the influence of variability in speech signals on the model’s performance. To this end, we conduct of set of controlled experiments using word-aligned read speech data in German. Our experiments show that (1) the model is more sensitive to dialectical variation than gender variation, and (2) recognition performance of word cognates from related languages reflect the degree of relatedness between languages in our study. Our work highlights the feasibility of modeling human speech perception using deep neural networks.</abstract>
<identifier type="citekey">mayn-etal-2021-familiar</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-srw.14</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-srw.14</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>96</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Familiar words but strange voices: Modelling the influence of speech variability on word recognition
%A Mayn, Alexandra
%A Abdullah, Badr M.
%A Klakow, Dietrich
%Y Sorodoc, Ionut-Teodor
%Y Sushil, Madhumita
%Y Takmaz, Ece
%Y Agirre, Eneko
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F mayn-etal-2021-familiar
%X We present a deep neural model of spoken word recognition which is trained to retrieve the meaning of a word (in the form of a word embedding) given its spoken form, a task which resembles that faced by a human listener. Furthermore, we investigate the influence of variability in speech signals on the model’s performance. To this end, we conduct of set of controlled experiments using word-aligned read speech data in German. Our experiments show that (1) the model is more sensitive to dialectical variation than gender variation, and (2) recognition performance of word cognates from related languages reflect the degree of relatedness between languages in our study. Our work highlights the feasibility of modeling human speech perception using deep neural networks.
%R 10.18653/v1/2021.eacl-srw.14
%U https://aclanthology.org/2021.eacl-srw.14
%U https://doi.org/10.18653/v1/2021.eacl-srw.14
%P 96-102
Markdown (Informal)
[Familiar words but strange voices: Modelling the influence of speech variability on word recognition](https://aclanthology.org/2021.eacl-srw.14) (Mayn et al., EACL 2021)
ACL