Investigating on incorporating pretrained and learnable speaker representations for multi-speaker multi-style text-to-speech
Journal
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Journal Volume
2021-June
Pages
8588-8592
Date Issued
2021
Author(s)
Abstract
The few-shot multi-speaker multi-style voice cloning task is to synthesize utterances with voice and speaking style similar to a reference speaker given only a few reference samples. In this work, we investigate different speaker representations and proposed to integrate pretrained and learnable speaker representations. Among different types of embeddings, the embedding pretrained by voice conversion achieves the best performance. The FastSpeech 2 model combined with both pretrained and learnable speaker representations shows great generalization ability on few-shot speakers and achieved 2nd place in the one-shot track of the ICASSP 2021 M2VoC challenge. ? 2021 IEEE
Subjects
Few-shot
Multi-speaker text-to-speech
Speaker representation
Clone cells
Embeddings
Generalization ability
Speaking styles
Text to speech
Voice conversion
Signal processing
SDGs
Type
conference paper