Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages

Autor:	Rouditchenko, Andrew, Khurana, Sameer, Thomas, Samuel, Feris, Rogerio, Karlinsky, Leonid, Kuehne, Hilde, Harwath, David, Kingsbury, Brian, Glass, James
Rok vydání:	2023
Předmět:	Computer Science - Computation and Language Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Recent models such as XLS-R and Whisper have made multilingual speech technologies more accessible by pre-training on audio from around 100 spoken languages each. However, there are thousands of spoken languages worldwide, and adapting to new languages is an important problem. In this work, we aim to understand which model adapts better to languages unseen during pre-training. We fine-tune both models on 13 unseen languages and 18 seen languages. Our results show that the number of hours seen per language and language family during pre-training is predictive of how the models compare, despite the significant differences in the pre-training methods. Comment: Accepted at Interspeech 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.12606 Zobrazit plný text záznamu View this record from Arxiv