Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings
Abstract
While speaker adaptation for end-to-end speech synthesis using speaker embeddings can produce good speaker similarity for speakers seen during training, there remains a gap for zero-shot adaptation to unseen speakers. We investigate multi-speaker modeling for end-to-end text-to-speech synthesis and study the effects of different types of state-of-the-art neural speaker embeddings on speaker similarity for unseen speakers. Learnable dictionary encoding-based speaker embeddings with angular softmax loss can improve equal error rates over x-vectors in a speaker verification task; these embeddings also improve speaker similarity and naturalness for unseen speakers when used for zero-shot adaptation to new speakers in end-to-end speech synthesis.
Keywords
Cite
@article{arxiv.1910.10838,
title = {Zero-Shot Multi-Speaker Text-To-Speech with State-of-the-art Neural Speaker Embeddings},
author = {Erica Cooper and Cheng-I Lai and Yusuke Yasuda and Fuming Fang and Xin Wang and Nanxin Chen and Junichi Yamagishi},
journal= {arXiv preprint arXiv:1910.10838},
year = {2020}
}
Comments
Accepted to ICASSP 2020