Data augmentation for low-resource Quechua ASR improvement

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Zevallos, Rodolfo
• dc.contributor.author Bel Rafecas, Núria
• dc.contributor.author Cámbara Ruiz, Guillermo
• dc.contributor.author Farrús, Mireia
• dc.contributor.author Luque, Jordi
• dc.date.accessioned 2023-03-13T07:15:53Z
• dc.date.available 2023-03-13T07:15:53Z
• dc.date.issued 2022
• dc.description Comunicació presentada a INTERSPEECH 2022, celebrat del 18 al 22 de setembre de 2022 a Inchon, Corea del Sud.
• dc.description.abstract Automatic Speech Recognition (ASR) is a key element in new services that helps users to interact with an automated system. Deep learning methods have made it possible to deploy systems with word error rates below 5% for ASR of English. However, the use of these methods is only available for languages with hundreds or thousands of hours of audio and their corresponding transcriptions. For the so-called low-resource languages to speed up the availability of resources that can improve the performance of their ASR systems, methods of creating new resources on the basis of existing ones are being investigated. In this paper we describe our data augmentation approach to improve the results of ASR models for low-resource and agglutinative languages. We carry out experiments developing an ASR for Quechua using the wav2letter++ model. We reduced WER by 8.73% through our approach to the base model. The resulting ASR model obtained 22.75% WER and was trained with 99 hours of original resources and 99 hours of synthetic data obtained with a combination of text augmentation and synthetic speech generation.
• dc.description.sponsorship This work has been partially supported by the Project PID2019-104512GB-I00, Ministerio de Ciencia e Innovación and Agencia Estatal de Investigación (Spain), and the INGENIOUS project from the European Union’s Horizon 2020 Research and Innovation Program under grant numbers 833435. The third author has been funded by the Agencia Estatal de Investigación (AEI), Ministerio de Ciencia, Innovación y Universidades and the Fondo Social Europeo (FSE) under grant RYC-2015-17239 (AEI/FSE, UE).
• dc.format.mimetype application/pdf
• dc.identifier.citation Zevallos R, Bel N, Cámbara G, Farrús M, Luque J. Data augmentation for low-resource Quechua ASR improvement. In: Proc. Interspeech 2022; 2022 Sep 18-22; Incheon, South Korea. [Baixas]: International Speech Communication Association; 2022. p. 3518-22. DOI: 10.21437/Interspeech.2022-770
• dc.identifier.doi http://dx.doi.org/10.21437/Interspeech.2022-770
• dc.identifier.uri http://hdl.handle.net/10230/56166
• dc.language.iso eng
• dc.publisher International Speech Communication Association (ISCA)
• dc.relation.ispartof Proc. Interspeech 2022; 2022 Sep 18-22; Incheon, South Korea. [Baixas]: International Speech Communication Association; 2022. p. 3518-22.
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/833435
• dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/PID2019-104512GB-I00
• dc.relation.projectID info:eu-repo/grantAgreement/ES/1PE/RYC-2015-17239
• dc.rights © 2022 ISCA
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Quechua
• dc.subject.keyword low-resource languages
• dc.subject.keyword data augmentation
• dc.subject.keyword Automatic Speech Recognition (ASR)
• dc.title Data augmentation for low-resource Quechua ASR improvement
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion