@inproceedings{ugan-etal-2024-decm-evaluating,
title = "{DECM}: Evaluating Bilingual {ASR} Performance on a Code-switching/mixing Benchmark",
author = "Ugan, Enes Yavuz and
Pham, Ngoc-Quan and
Waibel, Alexander",
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.400",
pages = "4468--4475",
abstract = "Automatic Speech Recognition has made significant progress, but challenges persist. Code-switched (CSW) Speech presents one such challenge, involving the mixing of multiple languages by a speaker. Even when multilingual ASR models are trained, each utterance on its own usually remains monolingual. We introduce an evaluation dataset for German-English CSW, with German as the matrix language and English as the embedded language. The dataset comprises spontaneous speech from diverse domains, enabling realistic CSW evaluation in German-English. It includes splits with varying degrees of CSW to facilitate specialized model analysis. As it is difficult to collect CSW data for all language pairs, the provision of such evaluation data, is crucial for developing and analyzing ASR models capable of generalizing across unseen pairs. Detailed data statistics are presented, and state-of-the-art (SOTA) multilingual models are evaluated showing challanges of CSW speech.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ugan-etal-2024-decm-evaluating">
<titleInfo>
<title>DECM: Evaluating Bilingual ASR Performance on a Code-switching/mixing Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Enes</namePart>
<namePart type="given">Yavuz</namePart>
<namePart type="family">Ugan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ngoc-Quan</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Waibel</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>Automatic Speech Recognition has made significant progress, but challenges persist. Code-switched (CSW) Speech presents one such challenge, involving the mixing of multiple languages by a speaker. Even when multilingual ASR models are trained, each utterance on its own usually remains monolingual. We introduce an evaluation dataset for German-English CSW, with German as the matrix language and English as the embedded language. The dataset comprises spontaneous speech from diverse domains, enabling realistic CSW evaluation in German-English. It includes splits with varying degrees of CSW to facilitate specialized model analysis. As it is difficult to collect CSW data for all language pairs, the provision of such evaluation data, is crucial for developing and analyzing ASR models capable of generalizing across unseen pairs. Detailed data statistics are presented, and state-of-the-art (SOTA) multilingual models are evaluated showing challanges of CSW speech.</abstract>
<identifier type="citekey">ugan-etal-2024-decm-evaluating</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.400</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4468</start>
<end>4475</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DECM: Evaluating Bilingual ASR Performance on a Code-switching/mixing Benchmark
%A Ugan, Enes Yavuz
%A Pham, Ngoc-Quan
%A Waibel, Alexander
%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 ugan-etal-2024-decm-evaluating
%X Automatic Speech Recognition has made significant progress, but challenges persist. Code-switched (CSW) Speech presents one such challenge, involving the mixing of multiple languages by a speaker. Even when multilingual ASR models are trained, each utterance on its own usually remains monolingual. We introduce an evaluation dataset for German-English CSW, with German as the matrix language and English as the embedded language. The dataset comprises spontaneous speech from diverse domains, enabling realistic CSW evaluation in German-English. It includes splits with varying degrees of CSW to facilitate specialized model analysis. As it is difficult to collect CSW data for all language pairs, the provision of such evaluation data, is crucial for developing and analyzing ASR models capable of generalizing across unseen pairs. Detailed data statistics are presented, and state-of-the-art (SOTA) multilingual models are evaluated showing challanges of CSW speech.
%U https://aclanthology.org/2024.lrec-main.400
%P 4468-4475
Markdown (Informal)
[DECM: Evaluating Bilingual ASR Performance on a Code-switching/mixing Benchmark](https://aclanthology.org/2024.lrec-main.400) (Ugan et al., LREC-COLING 2024)
ACL