Saved in:
Bibliographic Details
Main Authors: Gong, Cheng, Cooper, Erica, Wang, Xin, Qiang, Chunyu, Geng, Mengzhe, Wells, Dan, Wang, Longbiao, Dang, Jianwu, Tessier, Marc, Pine, Aidan, Richmond, Korin, Yamagishi, Junichi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.08911
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909223164575744
author Gong, Cheng
Cooper, Erica
Wang, Xin
Qiang, Chunyu
Geng, Mengzhe
Wells, Dan
Wang, Longbiao
Dang, Jianwu
Tessier, Marc
Pine, Aidan
Richmond, Korin
Yamagishi, Junichi
author_facet Gong, Cheng
Cooper, Erica
Wang, Xin
Qiang, Chunyu
Geng, Mengzhe
Wells, Dan
Wang, Longbiao
Dang, Jianwu
Tessier, Marc
Pine, Aidan
Richmond, Korin
Yamagishi, Junichi
contents Self-supervised learning (SSL) representations from massively multilingual models offer a promising solution for low-resource language speech tasks. Despite advancements, language adaptation in TTS systems remains an open problem. This paper explores the language adaptation capability of ZMM-TTS, a recent SSL-based multilingual TTS system proposed in our previous work. We conducted experiments on 12 languages using limited data with various fine-tuning configurations. We demonstrate that the similarity in phonetics between the pre-training and target languages, as well as the language category, affects the target language's adaptation performance. Additionally, we find that the fine-tuning dataset size and number of speakers influence adaptability. Surprisingly, we also observed that using paired data for fine-tuning is not always optimal compared to audio-only data. Beyond speech intelligibility, our analysis covers speaker similarity, language identification, and predicted MOS.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08911
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios
Gong, Cheng
Cooper, Erica
Wang, Xin
Qiang, Chunyu
Geng, Mengzhe
Wells, Dan
Wang, Longbiao
Dang, Jianwu
Tessier, Marc
Pine, Aidan
Richmond, Korin
Yamagishi, Junichi
Computation and Language
Audio and Speech Processing
Self-supervised learning (SSL) representations from massively multilingual models offer a promising solution for low-resource language speech tasks. Despite advancements, language adaptation in TTS systems remains an open problem. This paper explores the language adaptation capability of ZMM-TTS, a recent SSL-based multilingual TTS system proposed in our previous work. We conducted experiments on 12 languages using limited data with various fine-tuning configurations. We demonstrate that the similarity in phonetics between the pre-training and target languages, as well as the language category, affects the target language's adaptation performance. Additionally, we find that the fine-tuning dataset size and number of speakers influence adaptability. Surprisingly, we also observed that using paired data for fine-tuning is not always optimal compared to audio-only data. Beyond speech intelligibility, our analysis covers speaker similarity, language identification, and predicted MOS.
title An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios
topic Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2406.08911