ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gong, Cheng, Wang, Xin, Cooper, Erica, Wells, Dan, Wang, Longbiao, Dang, Jianwu, Richmond, Korin, Yamagishi, Junichi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913481471557632
author Gong, Cheng
Wang, Xin
Cooper, Erica
Wells, Dan
Wang, Longbiao
Dang, Jianwu
Richmond, Korin
Yamagishi, Junichi
author_facet Gong, Cheng
Wang, Xin
Cooper, Erica
Wells, Dan
Wang, Longbiao
Dang, Jianwu
Richmond, Korin
Yamagishi, Junichi
contents Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality audio data. TTS systems are typically built using a single speaker's voices, but there is growing interest in developing systems that can synthesize voices for new speakers using only a few seconds of their speech. This paper presents ZMM-TTS, a multilingual and multispeaker framework utilizing quantized latent speech representations from a large-scale, pre-trained, self-supervised model. Our paper combines text-based and speech-based self-supervised learning models for multilingual speech synthesis. Our proposed model has zero-shot generalization ability not only for unseen speakers but also for unseen languages. We have conducted comprehensive subjective and objective evaluations through a series of experiments. Our model has proven effective in terms of speech naturalness and similarity for both seen and unseen speakers in six high-resource languages. We also tested the efficiency of our method on two hypothetically low-resource languages. The results are promising, indicating that our proposed approach can synthesize audio that is intelligible and has a high degree of similarity to the target speaker's voice, even without any training data for the new, unseen language.
format Preprint
id arxiv_https___arxiv_org_abs_2312_14398
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations
Gong, Cheng
Wang, Xin
Cooper, Erica
Wells, Dan
Wang, Longbiao
Dang, Jianwu
Richmond, Korin
Yamagishi, Junichi
Sound
Audio and Speech Processing
Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker, single-language synthesis. Multilingual TTS systems are limited to resource-rich languages due to the lack of large paired text and studio-quality audio data. TTS systems are typically built using a single speaker's voices, but there is growing interest in developing systems that can synthesize voices for new speakers using only a few seconds of their speech. This paper presents ZMM-TTS, a multilingual and multispeaker framework utilizing quantized latent speech representations from a large-scale, pre-trained, self-supervised model. Our paper combines text-based and speech-based self-supervised learning models for multilingual speech synthesis. Our proposed model has zero-shot generalization ability not only for unseen speakers but also for unseen languages. We have conducted comprehensive subjective and objective evaluations through a series of experiments. Our model has proven effective in terms of speech naturalness and similarity for both seen and unseen speakers in six high-resource languages. We also tested the efficiency of our method on two hypothetically low-resource languages. The results are promising, indicating that our proposed approach can synthesize audio that is intelligible and has a high degree of similarity to the target speaker's voice, even without any training data for the new, unseen language.
title ZMM-TTS: Zero-shot Multilingual and Multispeaker Speech Synthesis Conditioned on Self-supervised Discrete Speech Representations
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2312.14398