@article{richter-etal-2017-evaluating,
title = "Evaluating Low-Level Speech Features Against Human Perceptual Data",
author = "Richter, Caitlin and
Feldman, Naomi H. and
Salgado, Harini and
Jansen, Aren",
editor = "Lee, Lillian and
Johnson, Mark and
Toutanova, Kristina",
journal = "Transactions of the Association for Computational Linguistics",
volume = "5",
year = "2017",
address = "Cambridge, MA",
publisher = "MIT Press",
url = "https://aclanthology.org/Q17-1030",
doi = "10.1162/tacl_a_00071",
pages = "425--440",
abstract = "We introduce a method for measuring the correspondence between low-level speech features and human perception, using a cognitive model of speech perception implemented directly on speech recordings. We evaluate two speaker normalization techniques using this method and find that in both cases, speech features that are normalized across speakers predict human data better than unnormalized speech features, consistent with previous research. Results further reveal differences across normalization methods in how well each predicts human data. This work provides a new framework for evaluating low-level representations of speech on their match to human perception, and lays the groundwork for creating more ecologically valid models of speech perception.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="richter-etal-2017-evaluating">
<titleInfo>
<title>Evaluating Low-Level Speech Features Against Human Perceptual Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Caitlin</namePart>
<namePart type="family">Richter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harini</namePart>
<namePart type="family">Salgado</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aren</namePart>
<namePart type="family">Jansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<genre authority="bibutilsgt">journal article</genre>
<relatedItem type="host">
<titleInfo>
<title>Transactions of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<issuance>continuing</issuance>
<publisher>MIT Press</publisher>
<place>
<placeTerm type="text">Cambridge, MA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">periodical</genre>
<genre authority="bibutilsgt">academic journal</genre>
</relatedItem>
<abstract>We introduce a method for measuring the correspondence between low-level speech features and human perception, using a cognitive model of speech perception implemented directly on speech recordings. We evaluate two speaker normalization techniques using this method and find that in both cases, speech features that are normalized across speakers predict human data better than unnormalized speech features, consistent with previous research. Results further reveal differences across normalization methods in how well each predicts human data. This work provides a new framework for evaluating low-level representations of speech on their match to human perception, and lays the groundwork for creating more ecologically valid models of speech perception.</abstract>
<identifier type="citekey">richter-etal-2017-evaluating</identifier>
<identifier type="doi">10.1162/tacl_a_00071</identifier>
<location>
<url>https://aclanthology.org/Q17-1030</url>
</location>
<part>
<date>2017</date>
<detail type="volume"><number>5</number></detail>
<extent unit="page">
<start>425</start>
<end>440</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Journal Article
%T Evaluating Low-Level Speech Features Against Human Perceptual Data
%A Richter, Caitlin
%A Feldman, Naomi H.
%A Salgado, Harini
%A Jansen, Aren
%J Transactions of the Association for Computational Linguistics
%D 2017
%V 5
%I MIT Press
%C Cambridge, MA
%F richter-etal-2017-evaluating
%X We introduce a method for measuring the correspondence between low-level speech features and human perception, using a cognitive model of speech perception implemented directly on speech recordings. We evaluate two speaker normalization techniques using this method and find that in both cases, speech features that are normalized across speakers predict human data better than unnormalized speech features, consistent with previous research. Results further reveal differences across normalization methods in how well each predicts human data. This work provides a new framework for evaluating low-level representations of speech on their match to human perception, and lays the groundwork for creating more ecologically valid models of speech perception.
%R 10.1162/tacl_a_00071
%U https://aclanthology.org/Q17-1030
%U https://doi.org/10.1162/tacl_a_00071
%P 425-440
Markdown (Informal)
[Evaluating Low-Level Speech Features Against Human Perceptual Data](https://aclanthology.org/Q17-1030) (Richter et al., TACL 2017)
ACL