Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation
Abstract
This paper presents a method for end-to-end cross-lingual text-to-speech (TTS) which aims to preserve the target language's pronunciation regardless of the original speaker's language. The model used is based on a non-attentive Tacotron architecture, where the decoder has been replaced with a normalizing flow network conditioned on the speaker identity, allowing both TTS and voice conversion (VC) to be performed by the same model due to the inherent linguistic content and speaker identity disentanglement. When used in a cross-lingual setting, acoustic features are initially produced with a native speaker of the target language and then voice conversion is applied by the same model in order to convert these features to the target speaker's voice. We verify through objective and subjective evaluations that our method can have benefits compared to baseline cross-lingual synthesis. By including speakers averaging 7.5 minutes of speech, we also present positive results on low-resource scenarios.
Cite
@article{arxiv.2210.17264,
title = {Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation},
author = {Nikolaos Ellinas and Georgios Vamvoukakis and Konstantinos Markopoulos and Georgia Maniati and Panos Kakoulidis and June Sig Sung and Inchul Hwang and Spyros Raptis and Aimilios Chalamandaris and Pirros Tsiakoulis},
journal= {arXiv preprint arXiv:2210.17264},
year = {2024}
}
Comments
Fundamental changes to the model described and experimental procedure