Voice Filter: Few-Shot Text-to-Speech Speaker Adaptation Using Voice Conversion as a Post-Processing Module
Authors:
- 23 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7902-7906
Abstract
State-of-the-art text-to-speech (TTS) systems require several hours of recorded speech data to generate high-quality synthetic speech. When using reduced amounts of training data, standard TTS models suffer from speech quality and intelligibility degradations, making training low-resource TTS systems problematic. In this paper, we propose a novel extremely low-resource TTS method called Voice Filter that uses as little as one minute of speech from a target speaker. It uses voice conversion (VC) as a post-processing module appended to a pre-existing high-quality TTS system and marks a conceptual shift in the existing TTS paradigm, framing the few-shot TTS problem as a VC task. Furthermore, we propose to use a duration-controllable TTS system to create a parallel speech corpus to facilitate the VC task. Results show that the Voice Filter outperforms state-of-the-art few-shot speech synthesis techniques in terms of objective and subjective metrics on one minute of speech on a diverse set of voices, while being competitive against a TTS model built on 30 times more data. 1Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net Architecture2020
- LRSpeech2020
- BOFFIN TTS: Few-Shot Speaker Adaptation by Bayesian Optimization2020
- End-to-End Text-to-Speech for Low-Resource Languages by Cross-Lingual Transfer Learning2019
- High Quality, Lightweight and Adaptable TTS Using LPCNet2019
- Semi-supervised Training for Improving Data Efficiency in End-to-end Speech Synthesis2019
- Effect of Data Reduction on Sequence-to-sequence Neural TTS2019
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling2019
- Generalized End-to-End Loss for Speaker Verification2018
- JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS2015