Improving Luxembourgish Speech Recognition with Cross-Lingual Speech Representations

Guardado en:
Detalles Bibliográficos
Publicado en:The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings (2023)
Autor principal: Nguyen, Le Minh
Otros Autores: Nayak, Shekhar, Coler, Matt
Publicado:
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Materias:
Acceso en línea:Citation/Abstract
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Resumen:Conference Title: 2022 IEEE Spoken Language Technology Workshop (SLT)Conference Start Date: 2023, Jan. 9 Conference End Date: 2023, Jan. 12 Conference Location: Doha, QatarLuxembourgish is a West Germanic language spoken by roughly 390,000 people, mainly in Luxembourg. It is one of Europe's under-described and under-resourced languages, not extensively investigated in the context of speech recognition. We explore the self-supervised multilingual learning of Luxembourgish speech representations for the speech recognition downstream task. We show that learning cross-lingual representations is essential for low-resourced languages such as Luxembourgish. Learning cross-lingual representations and rescoring the output transcriptions with language modelling while using only 4 hours of labelled speech achieves a word error rate of 15.1% and improves our Transfer Learning baseline model relatively by 33.1% and absolutely by 7.5%. Increasing the amount of labelled speech to 14 hours yields a significant performance gain resulting in a 9.3% word error rate.11Models and datasets are available at https://hugging£ace.co/lemswasabi
DOI:10.1109/SLT54892.2023.10022706
Fuente:Science Database