@inproceedings{evain-etal-2024-unraveling,
title = "Unraveling Spontaneous Speech Dimensions for Cross-Corpus {ASR} System Evaluation for {F}rench",
author = "Evain, Solene Virginie and
Rossato, Solange and
Portet, Fran{\c{c}}ois",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1491",
pages = "17165--17175",
abstract = "Many papers on speech processing use the term {`}spontaneous speech{'} as a catch-all term for situations like speaking with a friend, being interviewed on radio/TV or giving a lecture. However, Automatic Speech Recognition (ASR) systems performance seems to exhibit variation on this type of speech: the more spontaneous the speech, the higher the WER (Word Error Rate). Our study focuses on better understanding the elements influencing the levels of spontaneity in order to evaluate the relation between categories of spontaneity and ASR systems performance and improve the recognition on those categories. We first analyzed the literature, listed and unraveled those elements, and finally identified four axes: the situation of communication, the level of intimacy between speakers, the channel and the type of communication. Then, we trained ASR systems and measured the impact of instances of face-to-face interaction labeled with the previous dimensions (different levels of spontaneity) on WER. We made two axes vary and found that both dimensions have an impact on the WER. The situation of communication seems to have the biggest impact on spontaneity: ASR systems give better results for situations like an interview than for friends having a conversation at home.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="evain-etal-2024-unraveling">
<titleInfo>
<title>Unraveling Spontaneous Speech Dimensions for Cross-Corpus ASR System Evaluation for French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Solene</namePart>
<namePart type="given">Virginie</namePart>
<namePart type="family">Evain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Solange</namePart>
<namePart type="family">Rossato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Portet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many papers on speech processing use the term ‘spontaneous speech’ as a catch-all term for situations like speaking with a friend, being interviewed on radio/TV or giving a lecture. However, Automatic Speech Recognition (ASR) systems performance seems to exhibit variation on this type of speech: the more spontaneous the speech, the higher the WER (Word Error Rate). Our study focuses on better understanding the elements influencing the levels of spontaneity in order to evaluate the relation between categories of spontaneity and ASR systems performance and improve the recognition on those categories. We first analyzed the literature, listed and unraveled those elements, and finally identified four axes: the situation of communication, the level of intimacy between speakers, the channel and the type of communication. Then, we trained ASR systems and measured the impact of instances of face-to-face interaction labeled with the previous dimensions (different levels of spontaneity) on WER. We made two axes vary and found that both dimensions have an impact on the WER. The situation of communication seems to have the biggest impact on spontaneity: ASR systems give better results for situations like an interview than for friends having a conversation at home.</abstract>
<identifier type="citekey">evain-etal-2024-unraveling</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1491</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>17165</start>
<end>17175</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unraveling Spontaneous Speech Dimensions for Cross-Corpus ASR System Evaluation for French
%A Evain, Solene Virginie
%A Rossato, Solange
%A Portet, François
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F evain-etal-2024-unraveling
%X Many papers on speech processing use the term ‘spontaneous speech’ as a catch-all term for situations like speaking with a friend, being interviewed on radio/TV or giving a lecture. However, Automatic Speech Recognition (ASR) systems performance seems to exhibit variation on this type of speech: the more spontaneous the speech, the higher the WER (Word Error Rate). Our study focuses on better understanding the elements influencing the levels of spontaneity in order to evaluate the relation between categories of spontaneity and ASR systems performance and improve the recognition on those categories. We first analyzed the literature, listed and unraveled those elements, and finally identified four axes: the situation of communication, the level of intimacy between speakers, the channel and the type of communication. Then, we trained ASR systems and measured the impact of instances of face-to-face interaction labeled with the previous dimensions (different levels of spontaneity) on WER. We made two axes vary and found that both dimensions have an impact on the WER. The situation of communication seems to have the biggest impact on spontaneity: ASR systems give better results for situations like an interview than for friends having a conversation at home.
%U https://aclanthology.org/2024.lrec-main.1491
%P 17165-17175
Markdown (Informal)
[Unraveling Spontaneous Speech Dimensions for Cross-Corpus ASR System Evaluation for French](https://aclanthology.org/2024.lrec-main.1491) (Evain et al., LREC-COLING 2024)
ACL