https://scholars.lib.ntu.edu.tw/handle/123456789/638619
Title: | Personalized Lightweight Text-To-Speech: Voice Cloning with Adaptive Structured Pruning | Authors: | Huang, Sung Feng Chen, Chia Ping Chen, Zhi Sheng Tsai, Yu Pao HUNG-YI LEE |
Keywords: | few-shot | personalized TTS | structured pruning | trainable pruning | Voice cloning | Issue Date: | 1-Jan-2023 | Source: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | Abstract: | Personalized TTS is an exciting and highly desired application that allows users to train their TTS voice using only a few recordings. However, TTS training typically requires many hours of recording and a large model, making it unsuitable for deployment on mobile devices. To overcome this limitation, related works typically require fine-Tuning a pre-Trained TTS model to preserve its ability to generate high-quality audio samples while adapting to the target speaker's voice. This process is commonly referred to as "voice cloning."Although related works have achieved significant success in changing the TTS model's voice, they are still required to fine-Tune from a large pre-Trained model, resulting in a significant size for the voice-cloned model. In this paper, we propose applying trainable structured pruning to voice cloning. By training the structured pruning masks with voice-cloning data, we can produce a unique pruned model for each target speaker. Our experiments demonstrate that using learnable structured pruning, we can compress the model size to 7 times smaller while achieving comparable voice-cloning performance. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/638619 | ISBN: | 978-1-7281-6327-7 | ISSN: | 15206149 | DOI: | 10.1109/ICASSP49357.2023.10097178 |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.