Cross-lingual Multi-speaker Text-to-speech Synthesis for Voice Cloning without Using Parallel Corpus for Unseen Speakers

By Zhaoyu Liu, Brian Kan-Wing Mak. 2019

31 citations recorded by the source corpus.

We investigate a novel cross-lingual multi-speaker text-to-speech synthesis approach for generating high-quality native or accented speech for native/foreign seen/unseen speakers in English and Mandarin. The system consists of three separately trained components: an x-vector speaker encoder, a Tacotron-based synthesizer and a WaveNet vocoder. It is conditioned on 3 kinds of embeddings: (1) speaker embedding so that the system can be trained with speech from many speakers will little data from each speaker; (2) language embedding with shared phoneme inputs; (3) stress and tone embedding which improves naturalness of synthesized speech, especially for a tonal language like Mandarin. By adjusting the various embeddings, MOS results show that our method can generate high-quality natural and intelligible native speech for native/foreign seen/unseen speakers. Intelligibility and naturalness of accented speech is low as expected. Speaker similarity is good for native speech from native speakers. Interestingly, speaker similarity is also good for accented speech from foreign speakers. We also find that normalizing speaker embedding x-vectors by L2-norm normalization or whitening improves output quality a lot in many cases, and the WaveNet performance seems to be language-independent: our WaveNet is trained with Cantonese speech and can be used to generate Mandarin and English speech very well.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Lei He
6. Sheng Zhao
7. Mingxuan Wang
8. Yi Ren

In Signal Processing

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Lei He
6. Sheng Zhao
7. Fengpeng Yue
8. Qiao Tian

Citations in the corpus

• PolyVoice: Language Models for Speech to Speech Translation (2023, methodology): “Different embed-dings, such as speaker embedding, language embedding, and stress and tone embedding, are utilized in the cross-lingual TTS model to generate high-quality natural and intelligible native speech for native/foreign seen/unseen speakers (Liu and Mak, 2019).”
• A Survey on Neural Speech Synthesis (2021, background): “Adaptive General Adaptation AdaSpeech 1/3 [39, 398], [56, 260, 120, 37, 206]”
• Cross-Lingual Text-to-Speech Using Multi-Task Learning and Speaker Classifier Joint Training (2022, methodology): “Based on the encoder-decoder E2E framework, various multilingual text-to-speech (TTS) approaches have been proposed [7, 8, 9, 10, 11, 12, 13, 14].”