Multilingual Models for ASR in Chibchan Languages

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A9JRLFHVX" target="_blank" >RIV/00216208:11320/25:9JRLFHVX - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85200248556&partnerID=40&md5=4ce05a16cb985e771879e88dc9759f2c" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85200248556&partnerID=40&md5=4ce05a16cb985e771879e88dc9759f2c</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Multilingual Models for ASR in Chibchan Languages

Popis výsledku v původním jazyce

We present experiments on Automatic Speech Recognition (ASR) for Bribri and Cabécar, two languages from the Chibchan family. We finetune four ASR algorithms (Wav2Vec2, Whisper, MMS & WavLM) to create monolingual models, with the Wav2Vec2 model demonstrating the best performance. We then proceed to use Wav2Vec2 for (1) experiments on training joint and transfer learning models for both languages, and (2) an analysis of the errors, with a focus on the transcription of tone. Results show effective transfer learning for both Bribri and Cabécar, but especially for Bribri. A post-processing spell checking step further reduced character and word error rates. As for the errors, tone is where the Bribri models make the most errors, whereas the simpler tonal system of Cabécar is better transcribed by the model. Our work contributes to developing better ASR technology, an important tool that could facilitate transcription, one of the major bottlenecks in language documentation efforts. Our work also assesses how existing pre-trained models and algorithms perform for genuine extremely low resource-languages. ©2024 Association for Computational Linguistics.

Název v anglickém jazyce

Multilingual Models for ASR in Chibchan Languages

Popis výsledku anglicky

We present experiments on Automatic Speech Recognition (ASR) for Bribri and Cabécar, two languages from the Chibchan family. We finetune four ASR algorithms (Wav2Vec2, Whisper, MMS & WavLM) to create monolingual models, with the Wav2Vec2 model demonstrating the best performance. We then proceed to use Wav2Vec2 for (1) experiments on training joint and transfer learning models for both languages, and (2) an analysis of the errors, with a focus on the transcription of tone. Results show effective transfer learning for both Bribri and Cabécar, but especially for Bribri. A post-processing spell checking step further reduced character and word error rates. As for the errors, tone is where the Bribri models make the most errors, whereas the simpler tonal system of Cabécar is better transcribed by the model. Our work contributes to developing better ASR technology, an important tool that could facilitate transcription, one of the major bottlenecks in language documentation efforts. Our work also assesses how existing pre-trained models and algorithms perform for genuine extremely low resource-languages. ©2024 Association for Computational Linguistics.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proc. Conf. North American Chapter Assoc. Comput. Linguist.: Hum. Lang. Technol., NAACL

ISBN

979-889176114-8

ISSN

—

e-ISSN

—

Počet stran výsledku

15

Strana od-do

8513-8527

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

—

Místo konání akce

Mexico City, Mexico

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—