تقرير
ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation
العنوان: | ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation |
---|---|
المؤلفون: | Mehrish, Ambuj, Kashyap, Abhinav Ramesh, Yingting, Li, Majumder, Navonil, Poria, Soujanya |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Sound, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Electrical Engineering and Systems Science - Audio and Speech Processing |
الوصف: | There are significant challenges for speaker adaptation in text-to-speech for languages that are not widely spoken or for speakers with accents or dialects that are not well-represented in the training data. To address this issue, we propose the use of the "mixture of adapters" method. This approach involves adding multiple adapters within a backbone-model layer to learn the unique characteristics of different speakers. Our approach outperforms the baseline, with a noticeable improvement of 5% observed in speaker preference tests when using only one minute of data for each new speaker. Moreover, following the adapter paradigm, we fine-tune only the adapter parameters (11% of the total model parameters). This is a significant achievement in parameter-efficient speaker adaptation, and one of the first models of its kind. Overall, our proposed approach offers a promising solution to the speech synthesis techniques, particularly for adapting to speakers from diverse backgrounds. Comment: Interspeech 2023 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2305.18028 |
رقم الأكسشن: | edsarx.2305.18028 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |