@inproceedings{acfd7f788ce74ee09b14f6ed589224dd,
title = "AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation",
abstract = "Speaker adaptation in text-to-speech synthesis (TTS) is to fine-tune a pre-trained TTS model to adapt to new target speakers with limited data. While much effort has been conducted towards this task, seldom work has been performed for low computational resource scenarios due to the challenges raised by the requirement of the lightweight model and less computational complexity. In this paper, a tiny VITS-based [1] TTS model, named AdaVITS, for low computing resource speaker adaptation is proposed. To effectively reduce the parameters and computational complexity of VITS, an inverse short-time Fourier transform (iSTFT)-based wave construction decoder is proposed to replace the upsampling-based decoder which is resource-consuming in the original VITS. Besides, NanoFlow is introduced to share the density estimate across flow blocks to reduce the parameters of the prior encoder. Furthermore, to reduce the computational complexity of the textual encoder, scaled-dot attention is replaced with linear attention. To deal with the instability caused by the simplified model, we use phonetic posteriorgram (PPG) as a frame-level linguistic feature for supervising the model process from phoneme to spectrum. Experiments show that AdaVITS can generate stable and natural speech in speaker adaptation with 8. 97M model parameters and 0.72 GFlops computational complexity.1",
keywords = "adversarial learning, low computing resource, normalizing flows, speaker adaptation",
author = "Kun Song and Heyang Xue and Xinsheng Wang and Jian Cong and Yongmao Zhang and Lei Xie and Bing Yang and Xiong Zhang and Dan Su",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022 ; Conference date: 11-12-2022 Through 14-12-2022",
year = "2022",
doi = "10.1109/ISCSLP57327.2022.10037585",
language = "英语",
series = "2022 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "319--323",
editor = "Lee, {Kong Aik} and Hung-yi Lee and Yanfeng Lu and Minghui Dong",
booktitle = "2022 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022",
}