@inproceedings{galibert-etal-2016-generating,
title = "Generating Task-Pertinent sorted Error Lists for Speech Recognition",
author = "Galibert, Olivier and
Jannet, Mohamed Ameur Ben and
Kahn, Juliette and
Rosset, Sophie",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1297",
pages = "1883--1889",
abstract = "Automatic Speech recognition (ASR) is one of the most widely used components in spoken language processing applications. ASR errors are of varying importance with respect to the application, making error analysis keys to improving speech processing applications. Knowing the most serious errors for the applicative case is critical to build better systems. In the context of Automatic Speech Recognition (ASR) used as a first step towards Named Entity Recognition (NER) in speech, error seriousness is usually determined by their frequency, due to the use of the WER as metric to evaluate the ASR output, despite the emergence of more relevant measures in the literature. We propose to use a different evaluation metric form the literature in order to classify ASR errors according to their seriousness for NER. Our results show that the ASR errors importance is ranked differently depending on the used evaluation metric. A more detailed analysis shows that the estimation of the error impact given by the ATENE metric is more adapted to the NER task than the estimation based only on the most used frequency metric WER.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="galibert-etal-2016-generating">
<titleInfo>
<title>Generating Task-Pertinent sorted Error Lists for Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Galibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="given">Ameur</namePart>
<namePart type="given">Ben</namePart>
<namePart type="family">Jannet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juliette</namePart>
<namePart type="family">Kahn</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>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic Speech recognition (ASR) is one of the most widely used components in spoken language processing applications. ASR errors are of varying importance with respect to the application, making error analysis keys to improving speech processing applications. Knowing the most serious errors for the applicative case is critical to build better systems. In the context of Automatic Speech Recognition (ASR) used as a first step towards Named Entity Recognition (NER) in speech, error seriousness is usually determined by their frequency, due to the use of the WER as metric to evaluate the ASR output, despite the emergence of more relevant measures in the literature. We propose to use a different evaluation metric form the literature in order to classify ASR errors according to their seriousness for NER. Our results show that the ASR errors importance is ranked differently depending on the used evaluation metric. A more detailed analysis shows that the estimation of the error impact given by the ATENE metric is more adapted to the NER task than the estimation based only on the most used frequency metric WER.</abstract>
<identifier type="citekey">galibert-etal-2016-generating</identifier>
<location>
<url>https://aclanthology.org/L16-1297</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1883</start>
<end>1889</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Task-Pertinent sorted Error Lists for Speech Recognition
%A Galibert, Olivier
%A Jannet, Mohamed Ameur Ben
%A Kahn, Juliette
%A Rosset, Sophie
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F galibert-etal-2016-generating
%X Automatic Speech recognition (ASR) is one of the most widely used components in spoken language processing applications. ASR errors are of varying importance with respect to the application, making error analysis keys to improving speech processing applications. Knowing the most serious errors for the applicative case is critical to build better systems. In the context of Automatic Speech Recognition (ASR) used as a first step towards Named Entity Recognition (NER) in speech, error seriousness is usually determined by their frequency, due to the use of the WER as metric to evaluate the ASR output, despite the emergence of more relevant measures in the literature. We propose to use a different evaluation metric form the literature in order to classify ASR errors according to their seriousness for NER. Our results show that the ASR errors importance is ranked differently depending on the used evaluation metric. A more detailed analysis shows that the estimation of the error impact given by the ATENE metric is more adapted to the NER task than the estimation based only on the most used frequency metric WER.
%U https://aclanthology.org/L16-1297
%P 1883-1889
Markdown (Informal)
[Generating Task-Pertinent sorted Error Lists for Speech Recognition](https://aclanthology.org/L16-1297) (Galibert et al., LREC 2016)
ACL
- Olivier Galibert, Mohamed Ameur Ben Jannet, Juliette Kahn, and Sophie Rosset. 2016. Generating Task-Pertinent sorted Error Lists for Speech Recognition. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1883–1889, Portorož, Slovenia. European Language Resources Association (ELRA).