@inproceedings{goryainova-etal-2014-morpho,
title = "Morpho-Syntactic Study of Errors from Speech Recognition System",
author = "Goryainova, Maria and
Grouin, Cyril and
Rosset, Sophie and
Vasilescu, Ioana",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/383_Paper.pdf",
pages = "3045--3049",
abstract = "The study provides an original standpoint of the speech transcription errors by focusing on the morpho-syntactic features of the erroneous chunks and of the surrounding left and right context. The typology concerns the forms, the lemmas and the POS involved in erroneous chunks, and in the surrounding contexts. Comparison with error free contexts are also provided. The study is conducted on French. Morpho-syntactic analysis underlines that three main classes are particularly represented in the erroneous chunks: (i) grammatical words (to, of, the), (ii) auxiliary verbs (has, is), and (iii) modal verbs (should, must). Such items are widely encountered in the ASR outputs as frequent candidates to transcription errors. The analysis of the context points out that some left 3-grams contexts (e.g., repetitions, that is disfluencies, bracketing formulas such as {``}cest{''}, etc.) may be better predictors than others. Finally, the surface analysis conducted through a Levensthein distance analysis, highlighted that the most common distance is of 2 characters and mainly involves differences between inflected forms of a unique item.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goryainova-etal-2014-morpho">
<titleInfo>
<title>Morpho-Syntactic Study of Errors from Speech Recognition System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Goryainova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Grouin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Rosset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioana</namePart>
<namePart type="family">Vasilescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The study provides an original standpoint of the speech transcription errors by focusing on the morpho-syntactic features of the erroneous chunks and of the surrounding left and right context. The typology concerns the forms, the lemmas and the POS involved in erroneous chunks, and in the surrounding contexts. Comparison with error free contexts are also provided. The study is conducted on French. Morpho-syntactic analysis underlines that three main classes are particularly represented in the erroneous chunks: (i) grammatical words (to, of, the), (ii) auxiliary verbs (has, is), and (iii) modal verbs (should, must). Such items are widely encountered in the ASR outputs as frequent candidates to transcription errors. The analysis of the context points out that some left 3-grams contexts (e.g., repetitions, that is disfluencies, bracketing formulas such as “cest”, etc.) may be better predictors than others. Finally, the surface analysis conducted through a Levensthein distance analysis, highlighted that the most common distance is of 2 characters and mainly involves differences between inflected forms of a unique item.</abstract>
<identifier type="citekey">goryainova-etal-2014-morpho</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/383_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3045</start>
<end>3049</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morpho-Syntactic Study of Errors from Speech Recognition System
%A Goryainova, Maria
%A Grouin, Cyril
%A Rosset, Sophie
%A Vasilescu, Ioana
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F goryainova-etal-2014-morpho
%X The study provides an original standpoint of the speech transcription errors by focusing on the morpho-syntactic features of the erroneous chunks and of the surrounding left and right context. The typology concerns the forms, the lemmas and the POS involved in erroneous chunks, and in the surrounding contexts. Comparison with error free contexts are also provided. The study is conducted on French. Morpho-syntactic analysis underlines that three main classes are particularly represented in the erroneous chunks: (i) grammatical words (to, of, the), (ii) auxiliary verbs (has, is), and (iii) modal verbs (should, must). Such items are widely encountered in the ASR outputs as frequent candidates to transcription errors. The analysis of the context points out that some left 3-grams contexts (e.g., repetitions, that is disfluencies, bracketing formulas such as “cest”, etc.) may be better predictors than others. Finally, the surface analysis conducted through a Levensthein distance analysis, highlighted that the most common distance is of 2 characters and mainly involves differences between inflected forms of a unique item.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/383_Paper.pdf
%P 3045-3049
Markdown (Informal)
[Morpho-Syntactic Study of Errors from Speech Recognition System](http://www.lrec-conf.org/proceedings/lrec2014/pdf/383_Paper.pdf) (Goryainova et al., LREC 2014)
ACL
- Maria Goryainova, Cyril Grouin, Sophie Rosset, and Ioana Vasilescu. 2014. Morpho-Syntactic Study of Errors from Speech Recognition System. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3045–3049, Reykjavik, Iceland. European Language Resources Association (ELRA).