تقرير
Low-Resource Self-Supervised Learning with SSL-Enhanced TTS
العنوان: | Low-Resource Self-Supervised Learning with SSL-Enhanced TTS |
---|---|
المؤلفون: | Hsu, Po-chun, Elkahky, Ali, Hsu, Wei-Ning, Adi, Yossi, Nguyen, Tu Anh, Copet, Jade, Dupoux, Emmanuel, Lee, Hung-yi, Mohamed, Abdelrahman |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Electrical Engineering and Systems Science - Audio and Speech Processing, Computer Science - Sound |
الوصف: | 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 |
نوع الوثيقة: | Working Paper |
الوصول الحر: | http://arxiv.org/abs/2309.17020Test |
رقم الانضمام: | edsarx.2309.17020 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |