@inproceedings{ouzerrout-2024-universal,
title = "Universal-{WER}: Enhancing {WER} with Segmentation and Weighted Substitution for Varied Linguistic Contexts",
author = "Ouzerrout, Samy",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
Pirinen, Flammie and
Macias, Melany and
Crespo Avila, Mario},
booktitle = "Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages",
month = nov,
year = "2024",
address = "Helsinki, Finland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.iwclul-1.3",
pages = "29--35",
abstract = "Word Error Rate (WER) is a crucial metric for evaluating the performance of automatic speech recognition (ASR) systems. However, its traditional calculation, based on Levenshtein distance, does not account for lexical similarity between words and treats each substitution in a binary manner, while also ignoring segmentation errors. This paper proposes an improvement to WER by introducing a weighted substitution method, based on lexical similarity measures, and incorporating splitting and merging operations to better handle segmentation errors. Unlike other WER variants, our approach is easily integrable and generalizable to various languages, providing a more nuanced and accurate evaluation of ASR transcriptions, particularly for morphologically complex or low-resource languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ouzerrout-2024-universal">
<titleInfo>
<title>Universal-WER: Enhancing WER with Segmentation and Weighted Substitution for Varied Linguistic Contexts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samy</namePart>
<namePart type="family">Ouzerrout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melany</namePart>
<namePart type="family">Macias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Crespo Avila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Helsinki, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word Error Rate (WER) is a crucial metric for evaluating the performance of automatic speech recognition (ASR) systems. However, its traditional calculation, based on Levenshtein distance, does not account for lexical similarity between words and treats each substitution in a binary manner, while also ignoring segmentation errors. This paper proposes an improvement to WER by introducing a weighted substitution method, based on lexical similarity measures, and incorporating splitting and merging operations to better handle segmentation errors. Unlike other WER variants, our approach is easily integrable and generalizable to various languages, providing a more nuanced and accurate evaluation of ASR transcriptions, particularly for morphologically complex or low-resource languages.</abstract>
<identifier type="citekey">ouzerrout-2024-universal</identifier>
<location>
<url>https://aclanthology.org/2024.iwclul-1.3</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>29</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Universal-WER: Enhancing WER with Segmentation and Weighted Substitution for Varied Linguistic Contexts
%A Ouzerrout, Samy
%Y Hämäläinen, Mika
%Y Pirinen, Flammie
%Y Macias, Melany
%Y Crespo Avila, Mario
%S Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages
%D 2024
%8 November
%I Association for Computational Linguistics
%C Helsinki, Finland
%F ouzerrout-2024-universal
%X Word Error Rate (WER) is a crucial metric for evaluating the performance of automatic speech recognition (ASR) systems. However, its traditional calculation, based on Levenshtein distance, does not account for lexical similarity between words and treats each substitution in a binary manner, while also ignoring segmentation errors. This paper proposes an improvement to WER by introducing a weighted substitution method, based on lexical similarity measures, and incorporating splitting and merging operations to better handle segmentation errors. Unlike other WER variants, our approach is easily integrable and generalizable to various languages, providing a more nuanced and accurate evaluation of ASR transcriptions, particularly for morphologically complex or low-resource languages.
%U https://aclanthology.org/2024.iwclul-1.3
%P 29-35
Markdown (Informal)
[Universal-WER: Enhancing WER with Segmentation and Weighted Substitution for Varied Linguistic Contexts](https://aclanthology.org/2024.iwclul-1.3) (Ouzerrout, IWCLUL 2024)
ACL