@inproceedings{kronis-etal-2024-code-mixed,
title = "Code-Mixed Text Augmentation for {L}atvian {ASR}",
author = "Kronis, Martins and
Salimbajevs, Askars and
Pinnis, M{\=a}rcis",
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.308",
pages = "3469--3479",
abstract = "Code-mixing has become mainstream in the modern, globalised world and affects low-resource languages, such as Latvian, in particular. Solutions to developing an automatic speech recognition system (ASR) for code-mixed speech often rely on specially created audio-text corpora, which are expensive and time-consuming to create. In this work, we attempt to tackle code-mixed Latvian-English speech recognition by improving the language model (LM) of a hybrid ASR system. We make a distinction between inflected transliterations and phonetic transcriptions as two different foreign word types. We propose an inflected transliteration model and a phonetic transcription model for the automatic generation of said word types. We then leverage a large human-translated English-Latvian parallel text corpus to generate synthetic code-mixed Latvian sentences by substituting in generated foreign words. Using the newly created augmented corpora, we train a new LM and combine it with our existing Latvian acoustic model (AM). For evaluation, we create a specialised foreign word test set on which our methods yield up to 15{\%} relative CER improvement. We then further validate these results in a human evaluation campaign.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kronis-etal-2024-code-mixed">
<titleInfo>
<title>Code-Mixed Text Augmentation for Latvian ASR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martins</namePart>
<namePart type="family">Kronis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Askars</namePart>
<namePart type="family">Salimbajevs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mārcis</namePart>
<namePart type="family">Pinnis</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>Code-mixing has become mainstream in the modern, globalised world and affects low-resource languages, such as Latvian, in particular. Solutions to developing an automatic speech recognition system (ASR) for code-mixed speech often rely on specially created audio-text corpora, which are expensive and time-consuming to create. In this work, we attempt to tackle code-mixed Latvian-English speech recognition by improving the language model (LM) of a hybrid ASR system. We make a distinction between inflected transliterations and phonetic transcriptions as two different foreign word types. We propose an inflected transliteration model and a phonetic transcription model for the automatic generation of said word types. We then leverage a large human-translated English-Latvian parallel text corpus to generate synthetic code-mixed Latvian sentences by substituting in generated foreign words. Using the newly created augmented corpora, we train a new LM and combine it with our existing Latvian acoustic model (AM). For evaluation, we create a specialised foreign word test set on which our methods yield up to 15% relative CER improvement. We then further validate these results in a human evaluation campaign.</abstract>
<identifier type="citekey">kronis-etal-2024-code-mixed</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.308</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3469</start>
<end>3479</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Code-Mixed Text Augmentation for Latvian ASR
%A Kronis, Martins
%A Salimbajevs, Askars
%A Pinnis, Mārcis
%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 kronis-etal-2024-code-mixed
%X Code-mixing has become mainstream in the modern, globalised world and affects low-resource languages, such as Latvian, in particular. Solutions to developing an automatic speech recognition system (ASR) for code-mixed speech often rely on specially created audio-text corpora, which are expensive and time-consuming to create. In this work, we attempt to tackle code-mixed Latvian-English speech recognition by improving the language model (LM) of a hybrid ASR system. We make a distinction between inflected transliterations and phonetic transcriptions as two different foreign word types. We propose an inflected transliteration model and a phonetic transcription model for the automatic generation of said word types. We then leverage a large human-translated English-Latvian parallel text corpus to generate synthetic code-mixed Latvian sentences by substituting in generated foreign words. Using the newly created augmented corpora, we train a new LM and combine it with our existing Latvian acoustic model (AM). For evaluation, we create a specialised foreign word test set on which our methods yield up to 15% relative CER improvement. We then further validate these results in a human evaluation campaign.
%U https://aclanthology.org/2024.lrec-main.308
%P 3469-3479
Markdown (Informal)
[Code-Mixed Text Augmentation for Latvian ASR](https://aclanthology.org/2024.lrec-main.308) (Kronis et al., LREC-COLING 2024)
ACL
- Martins Kronis, Askars Salimbajevs, and Mārcis Pinnis. 2024. Code-Mixed Text Augmentation for Latvian ASR. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3469–3479, Torino, Italia. ELRA and ICCL.