Exploring Timbre Disentanglement in Non-Autoregressive Cross-Lingual Text-to-Speech
Haoyue Zhan, Xinyuan Yu, Haitong Zhang, Yang Zhang, Yue Lin · Interspeech 2022 · 2022
In this paper, we study the disentanglement of speaker and language representations in non-autoregressive cross-lingual TTS models from various aspects.We propose a phoneme length regulator that solves the length mismatch problem between IPA input sequence and monolingual alignment results.Using the phoneme length regulator, we present a FastPitch-based crosslingual model with IPA symbols as input representations.Our experiments show that language-independent input representations (e.g.IPA symbols), an increasing number of training speakers, and explicit modeling of speech variance information all encourage non-autoregressive cross-lingual TTS model to disentangle speaker and language representations.The subjective evaluation shows that our proposed model can achieve decent naturalness and speaker similarity in cross-language voice cloning.