LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus

被引：5

作者：

Koizumi, Yuma ^{[1
]}

Zen, Heiga ^{[1
]}

Karita, Shigeki ^{[1
]}

Ding, Yifan ^{[1
]}

Yatabe, Kohei ^{[2
]}

Morioka, Nobuyuki ^{[1
]}

Bacchiani, Michiel ^{[1
]}

Zhang, Yu ^{[3
]}

Han, Wei ^{[3
]}

Bapna, Ankur ^{[3
]}

机构：

[1] Google, Tokyo, Japan

[2] Tokyo Univ Agr Technol, Tokyo, Japan

[3] Google, Mountain View, CA USA

来源：

INTERSPEECH 2023 | 2023年

关键词：

Text-to-speech; dataset; speech restoration;

D O I：

10.21437/Interspeech.2023-1584

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

This paper introduces a new speech dataset called "LibriTTS-R" designed for text-to-speech (TTS) use. It is derived by applying speech restoration to the LibriTTS corpus, which consists of 585 hours of speech data at 24 kHz sampling rate from 2,456 speakers and the corresponding texts. The constituent samples of LibriTTS-R are identical to those of LibriTTS, with only the sound quality improved. Experimental results show that the LibriTTS-R ground-truth samples showed significantly improved sound quality compared to those in LibriTTS. In addition, neural end-to-end TTS trained with LibriTTS-R achieved speech naturalness on par with that of the ground-truth samples. The corpus is freely available for download from http: //www.openslr.org/141/.

引用

页码：5496 / 5500

页数：5

共 50 条

[1] DeepMine-multi-TTS: a Persian speech corpus for multi-speaker text-to-speech
Adibian, Majid
Zeinali, Hossein
Barmaki, Soroush
LANGUAGE RESOURCES AND EVALUATION, 2025,
[2] Multi-speaker Emotional Text-to-speech Synthesizer
Cho, Sungjae
Lee, Soo-Young
INTERSPEECH 2021, 2021, : 2337 - 2338
[3] Multi-Speaker Text-to-Speech Training With Speaker Anonymized Data
Huang, Wen-Chin
Wu, Yi-Chiao
Toda, Tomoki
IEEE SIGNAL PROCESSING LETTERS, 2024, 31 : 2995 - 2999
[4] LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
Zen, Heiga
Dang, Viet
Clark, Rob
Zhang, Yu
Weiss, Ron J.
Jia, Ye
Chen, Zhifeng
Wu, Yonghui
INTERSPEECH 2019, 2019, : 1526 - 1530
[5] Deep Voice 2: Multi-Speaker Neural Text-to-Speech
Arik, Sercan O.
Diamos, Gregory
Gibiansky, Andrew
Miller, John
Peng, Kainan
Ping, Wei
Raiman, Jonathan
Zhou, Yanqi
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[6] ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis
Xue, Jinlong
Deng, Yayue
Han, Yichen
Li, Ya
Sun, Jianqing
Liang, Jiaen
2022 13TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2022, : 230 - 234
[7] Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech
Singh, Abhayjeet
Nagireddi, Amala
Jayakumar, Anjali
Deekshitha, G.
Bandekar, Jesuraja
Roopa, R.
Badiger, Sandhya
Udupa, Sathvik
Kumar, Saurabh
Ghosh, Prasanta Kumar
Murthy, Hema A.
Zen, Heiga
Kumar, Pranaw
Kant, Kamal
Bole, Amol
Singh, Bira Chandra
Tokuda, Keiichi
Hasegawa-Johnson, Mark
Olbrich, Philipp
IEEE OPEN JOURNAL OF SIGNAL PROCESSING, 2024, 5 : 790 - 798
[8] Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes
Mitsui, Kentaro
Koriyama, Tomoki
Saruwatari, Hiroshi
INTERSPEECH 2020, 2020, : 2032 - 2036
[9] LIGHTSPEECH: LIGHTWEIGHT NON-AUTOREGRESSIVE MULTI-SPEAKER TEXT-TO-SPEECH
Li, Song
Ouyang, Beibei
Li, Lin
Hong, Qingyang
2021 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP (SLT), 2021, : 499 - 506
[10] LibriTTS-P: A Corpus with Speaking Style and Speaker Identity Prompts for Text-to-Speech and Style Captioning
Kawamura, Masaya
Yamamoto, Ryuichi
Shirahata, Yuma
Hasumi, Takuya
Tachibana, Kentaro
INTERSPEECH 2024, 2024, : 1850 - 1854

← 1 2 3 4 5 →