Skip to main content

AISHELL-3: A multi-speaker Mandarin TTS corpus

Publication ,  Conference
Shi, Y; Bu, H; Xu, X; Zhang, S; Li, M
Published in: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
January 1, 2021

In this paper, we present AISHELL-3 †, a large-scale multispeaker Mandarin speech corpus which could be used to train multi-speaker Text-To-Speech (TTS) systems. The corpus contains roughly 85 hours of emotion-neutral recordings spanning across 218 native Chinese mandarin speakers. Their auxiliary attributes such as gender, age group and native accents are explicitly marked and provided in the corpus. Moreover, transcripts in Chinese character-level and pinyin-level are provided along with the recordings. We also present some data processing strategies and techniques which match with the characteristics of the presented corpus and conduct experiments on multiple speech-synthesis systems to assess the quality of the generated speech samples, showing promising results. The corpus is available online at openslr.org/93/under Apache v2.0 license.

Duke Scholars

Published In

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

DOI

EISSN

1990-9772

ISSN

2308-457X

Publication Date

January 1, 2021

Volume

5

Start / End Page

3526 / 3530
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Shi, Y., Bu, H., Xu, X., Zhang, S., & Li, M. (2021). AISHELL-3: A multi-speaker Mandarin TTS corpus. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (Vol. 5, pp. 3526–3530). https://doi.org/10.21437/Interspeech.2021-755
Shi, Y., H. Bu, X. Xu, S. Zhang, and M. Li. “AISHELL-3: A multi-speaker Mandarin TTS corpus.” In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 5:3526–30, 2021. https://doi.org/10.21437/Interspeech.2021-755.
Shi Y, Bu H, Xu X, Zhang S, Li M. AISHELL-3: A multi-speaker Mandarin TTS corpus. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2021. p. 3526–30.
Shi, Y., et al. “AISHELL-3: A multi-speaker Mandarin TTS corpus.” Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 5, 2021, pp. 3526–30. Scopus, doi:10.21437/Interspeech.2021-755.
Shi Y, Bu H, Xu X, Zhang S, Li M. AISHELL-3: A multi-speaker Mandarin TTS corpus. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2021. p. 3526–3530.

Published In

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

DOI

EISSN

1990-9772

ISSN

2308-457X

Publication Date

January 1, 2021

Volume

5

Start / End Page

3526 / 3530