@inproceedings{dhawan-etal-2023-unified,
title = "Unified Model for Code-Switching Speech Recognition and Language Identification Based on Concatenated Tokenizer",
author = "Dhawan, Kunal and
Rekesh, KDimating and
Ginsburg, Boris",
editor = "Winata, Genta and
Kar, Sudipta and
Zhukova, Marina and
Solorio, Thamar and
Diab, Mona and
Sitaram, Sunayana and
Choudhury, Monojit and
Bali, Kalika",
booktitle = "Proceedings of the 6th Workshop on Computational Approaches to Linguistic Code-Switching",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.calcs-1.7",
doi = "10.18653/v1/2023.calcs-1.7",
pages = "74--82",
abstract = "Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper proposes (1) a new method for creating code-switching ASR datasets from purely monolingual data sources, and (2) a novel Concatenated Tokenizer that enables ASR models to generate language ID for each emitted text token while reusing existing monolingual tokenizers. The efficacy of these approaches for building CS ASR models is demonstrated for two language pairs, English-Hindi and English-Spanish, where we achieve new state-of-the-art results on the Miami Bangor CS evaluation corpus. In addition to competitive ASR performance, the proposed Concatenated Tokenizer models are highly effective for spoken language identification, achieving 98{\%}+ accuracy on the out-of-distribution FLEURS dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhawan-etal-2023-unified">
<titleInfo>
<title>Unified Model for Code-Switching Speech Recognition and Language Identification Based on Concatenated Tokenizer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kunal</namePart>
<namePart type="family">Dhawan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">KDimating</namePart>
<namePart type="family">Rekesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boris</namePart>
<namePart type="family">Ginsburg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Computational Approaches to Linguistic Code-Switching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Genta</namePart>
<namePart type="family">Winata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudipta</namePart>
<namePart type="family">Kar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Zhukova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monojit</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper proposes (1) a new method for creating code-switching ASR datasets from purely monolingual data sources, and (2) a novel Concatenated Tokenizer that enables ASR models to generate language ID for each emitted text token while reusing existing monolingual tokenizers. The efficacy of these approaches for building CS ASR models is demonstrated for two language pairs, English-Hindi and English-Spanish, where we achieve new state-of-the-art results on the Miami Bangor CS evaluation corpus. In addition to competitive ASR performance, the proposed Concatenated Tokenizer models are highly effective for spoken language identification, achieving 98%+ accuracy on the out-of-distribution FLEURS dataset.</abstract>
<identifier type="citekey">dhawan-etal-2023-unified</identifier>
<identifier type="doi">10.18653/v1/2023.calcs-1.7</identifier>
<location>
<url>https://aclanthology.org/2023.calcs-1.7</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>74</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unified Model for Code-Switching Speech Recognition and Language Identification Based on Concatenated Tokenizer
%A Dhawan, Kunal
%A Rekesh, KDimating
%A Ginsburg, Boris
%Y Winata, Genta
%Y Kar, Sudipta
%Y Zhukova, Marina
%Y Solorio, Thamar
%Y Diab, Mona
%Y Sitaram, Sunayana
%Y Choudhury, Monojit
%Y Bali, Kalika
%S Proceedings of the 6th Workshop on Computational Approaches to Linguistic Code-Switching
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F dhawan-etal-2023-unified
%X Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper proposes (1) a new method for creating code-switching ASR datasets from purely monolingual data sources, and (2) a novel Concatenated Tokenizer that enables ASR models to generate language ID for each emitted text token while reusing existing monolingual tokenizers. The efficacy of these approaches for building CS ASR models is demonstrated for two language pairs, English-Hindi and English-Spanish, where we achieve new state-of-the-art results on the Miami Bangor CS evaluation corpus. In addition to competitive ASR performance, the proposed Concatenated Tokenizer models are highly effective for spoken language identification, achieving 98%+ accuracy on the out-of-distribution FLEURS dataset.
%R 10.18653/v1/2023.calcs-1.7
%U https://aclanthology.org/2023.calcs-1.7
%U https://doi.org/10.18653/v1/2023.calcs-1.7
%P 74-82
Markdown (Informal)
[Unified Model for Code-Switching Speech Recognition and Language Identification Based on Concatenated Tokenizer](https://aclanthology.org/2023.calcs-1.7) (Dhawan et al., CALCS-WS 2023)
ACL