@inproceedings{morcillo-etal-2024-automatic-speech,
title = "Automatic Speech Recognition for {G}ascon and Languedocian Variants of {O}ccitan",
author = {Morcillo, I{\~n}igo and
Leturia, Igor and
Corral, Ander and
Sarasola, Xabier and
Barret, Micha{\"e}l and
S{\'e}guier, Aure and
Daz{\'e}as, Benaset},
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.177",
pages = "1969--1978",
abstract = "This paper describes different approaches for developing, for the first time, an automatic speech recognition system for two of the main dialects of Occitan, namely Gascon and Languedocian, and the results obtained in them. The difficulty of the task lies in the fact that Occitan is a less-resourced language. Although a great effort has been made to collect or create corpora of each variant (transcribed speech recordings for the acoustic models and two text corpora for the language models), the sizes of the corpora obtained are far from those of successful systems reported in the literature, and thus we have tested different techniques to compensate for the lack of resources. We have developed classical systems using Kaldi, creating an acoustic model for each variant and also creating language models from the collected corpora and from machine translated texts. We have also tried fine-tuning a Whisper model with our speech corpora. We report word error rates of 20.86 for Gascon and 13.52 for Languedocian with the Kaldi systems and 16.37 for Gascon and 11.74 for Languedocian with Whisper.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morcillo-etal-2024-automatic-speech">
<titleInfo>
<title>Automatic Speech Recognition for Gascon and Languedocian Variants of Occitan</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iñigo</namePart>
<namePart type="family">Morcillo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Leturia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ander</namePart>
<namePart type="family">Corral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xabier</namePart>
<namePart type="family">Sarasola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michaël</namePart>
<namePart type="family">Barret</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aure</namePart>
<namePart type="family">Séguier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benaset</namePart>
<namePart type="family">Dazéas</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>This paper describes different approaches for developing, for the first time, an automatic speech recognition system for two of the main dialects of Occitan, namely Gascon and Languedocian, and the results obtained in them. The difficulty of the task lies in the fact that Occitan is a less-resourced language. Although a great effort has been made to collect or create corpora of each variant (transcribed speech recordings for the acoustic models and two text corpora for the language models), the sizes of the corpora obtained are far from those of successful systems reported in the literature, and thus we have tested different techniques to compensate for the lack of resources. We have developed classical systems using Kaldi, creating an acoustic model for each variant and also creating language models from the collected corpora and from machine translated texts. We have also tried fine-tuning a Whisper model with our speech corpora. We report word error rates of 20.86 for Gascon and 13.52 for Languedocian with the Kaldi systems and 16.37 for Gascon and 11.74 for Languedocian with Whisper.</abstract>
<identifier type="citekey">morcillo-etal-2024-automatic-speech</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.177</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1969</start>
<end>1978</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Speech Recognition for Gascon and Languedocian Variants of Occitan
%A Morcillo, Iñigo
%A Leturia, Igor
%A Corral, Ander
%A Sarasola, Xabier
%A Barret, Michaël
%A Séguier, Aure
%A Dazéas, Benaset
%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 morcillo-etal-2024-automatic-speech
%X This paper describes different approaches for developing, for the first time, an automatic speech recognition system for two of the main dialects of Occitan, namely Gascon and Languedocian, and the results obtained in them. The difficulty of the task lies in the fact that Occitan is a less-resourced language. Although a great effort has been made to collect or create corpora of each variant (transcribed speech recordings for the acoustic models and two text corpora for the language models), the sizes of the corpora obtained are far from those of successful systems reported in the literature, and thus we have tested different techniques to compensate for the lack of resources. We have developed classical systems using Kaldi, creating an acoustic model for each variant and also creating language models from the collected corpora and from machine translated texts. We have also tried fine-tuning a Whisper model with our speech corpora. We report word error rates of 20.86 for Gascon and 13.52 for Languedocian with the Kaldi systems and 16.37 for Gascon and 11.74 for Languedocian with Whisper.
%U https://aclanthology.org/2024.lrec-main.177
%P 1969-1978
Markdown (Informal)
[Automatic Speech Recognition for Gascon and Languedocian Variants of Occitan](https://aclanthology.org/2024.lrec-main.177) (Morcillo et al., LREC-COLING 2024)
ACL
- Iñigo Morcillo, Igor Leturia, Ander Corral, Xabier Sarasola, Michaël Barret, Aure Séguier, and Benaset Dazéas. 2024. Automatic Speech Recognition for Gascon and Languedocian Variants of Occitan. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1969–1978, Torino, Italia. ELRA and ICCL.