Low-Resource Self-Supervised Learning with SSL-Enhanced TTS

Autor:	Hsu, Po-chun, Elkahky, Ali, Hsu, Wei-Ning, Adi, Yossi, Nguyen, Tu Anh, Copet, Jade, Dupoux, Emmanuel, Lee, Hung-yi, Mohamed, Abdelrahman
Rok vydání:	2023
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	Self-supervised learning (SSL) techniques have achieved remarkable results in various speech processing tasks. Nonetheless, a significant challenge remains in reducing the reliance on vast amounts of speech data for pre-training. This paper proposes to address this challenge by leveraging synthetic speech to augment a low-resource pre-training corpus. We construct a high-quality text-to-speech (TTS) system with limited resources using SSL features and generate a large synthetic corpus for pre-training. Experimental results demonstrate that our proposed approach effectively reduces the demand for speech data by 90% with only slight performance degradation. To the best of our knowledge, this is the first work aiming to enhance low-resource self-supervised learning in speech processing. Comment: ASRU 2023 SPARKS Workshop
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2309.17020 Zobrazit plný text záznamu View this record from Arxiv