@inproceedings{huet-etal-2008-morphosyntactic,
title = "Morphosyntactic Resources for Automatic Speech Recognition",
author = "Huet, St{\'e}phane and
Gravier, Guillaume and
S{\'e}billot, Pascale",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}`08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L08-1496/",
abstract = "Texts generated by automatic speech recognition (ASR) systems have some specificities, related to the idiosyncrasies of oral productions or the principles of ASR systems, that make them more difficult to exploit than more conventional natural language written texts. This paper aims at studying the interest of morphosyntactic information as a useful resource for ASR. We show the ability of automatic methods to tag outputs of ASR systems, by obtaining a tag accuracy similar for automatic transcriptions to the 95-98 {\%} usually reported for written texts, such as newspapers. We also demonstrate experimentally that tagging is useful to improve the quality of transcriptions by using morphosyntactic information in a post-processing stage of speech decoding. Indeed, we obtain a significant decrease of the word error rate with experiments done on French broadcast news from the ESTER corpus; we also notice an improvement of the sentence error rate and observe that a significant number of agreement errors are corrected."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huet-etal-2008-morphosyntactic">
<titleInfo>
<title>Morphosyntactic Resources for Automatic Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stéphane</namePart>
<namePart type="family">Huet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Gravier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Sébillot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC‘08)</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">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Texts generated by automatic speech recognition (ASR) systems have some specificities, related to the idiosyncrasies of oral productions or the principles of ASR systems, that make them more difficult to exploit than more conventional natural language written texts. This paper aims at studying the interest of morphosyntactic information as a useful resource for ASR. We show the ability of automatic methods to tag outputs of ASR systems, by obtaining a tag accuracy similar for automatic transcriptions to the 95-98 % usually reported for written texts, such as newspapers. We also demonstrate experimentally that tagging is useful to improve the quality of transcriptions by using morphosyntactic information in a post-processing stage of speech decoding. Indeed, we obtain a significant decrease of the word error rate with experiments done on French broadcast news from the ESTER corpus; we also notice an improvement of the sentence error rate and observe that a significant number of agreement errors are corrected.</abstract>
<identifier type="citekey">huet-etal-2008-morphosyntactic</identifier>
<location>
<url>https://aclanthology.org/L08-1496/</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphosyntactic Resources for Automatic Speech Recognition
%A Huet, Stéphane
%A Gravier, Guillaume
%A Sébillot, Pascale
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC‘08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F huet-etal-2008-morphosyntactic
%X Texts generated by automatic speech recognition (ASR) systems have some specificities, related to the idiosyncrasies of oral productions or the principles of ASR systems, that make them more difficult to exploit than more conventional natural language written texts. This paper aims at studying the interest of morphosyntactic information as a useful resource for ASR. We show the ability of automatic methods to tag outputs of ASR systems, by obtaining a tag accuracy similar for automatic transcriptions to the 95-98 % usually reported for written texts, such as newspapers. We also demonstrate experimentally that tagging is useful to improve the quality of transcriptions by using morphosyntactic information in a post-processing stage of speech decoding. Indeed, we obtain a significant decrease of the word error rate with experiments done on French broadcast news from the ESTER corpus; we also notice an improvement of the sentence error rate and observe that a significant number of agreement errors are corrected.
%U https://aclanthology.org/L08-1496/
Markdown (Informal)
[Morphosyntactic Resources for Automatic Speech Recognition](https://aclanthology.org/L08-1496/) (Huet et al., LREC 2008)
ACL
- Stéphane Huet, Guillaume Gravier, and Pascale Sébillot. 2008. Morphosyntactic Resources for Automatic Speech Recognition. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).