An Unsupervised Method to Select a Speaker Subset from Large Multi-Speaker Speech Synthesis Datasets

被引：2

作者：

Gallegos, Pilar Oplustil ^{[1
]}

Williams, Jennifer ^{[1
]}

Rownicka, Joanna ^{[1
]}

King, Simon ^{[1
]}

机构：

[1] Univ Edinburgh, Ctr Speech Technol Res, Edinburgh, Midlothian, Scotland

来源：

INTERSPEECH 2020 | 2020年

基金：

英国工程与自然科学研究理事会;

关键词：

speech synthesis; data; clustering; speaker representation; sequence-to-sequence models; multi-speaker;

D O I：

10.21437/Interspeech.2020-2567

中图分类号：

R36 [病理学]; R76 [耳鼻咽喉科学];

学科分类号：

100104 ; 100213 ;

摘要：

Large multi-speaker datasets for TTS typically contain diverse speakers, recording conditions, styles and quality of data. Although one might generally presume that more data is better, in this paper we show that a model trained on a carefully-chosen subset of speakers from LibriTTS provides significantly better quality synthetic speech than a model trained on a larger set. We propose an unsupervised methodology to find this subset by clustering per-speaker acoustic representations.

引用

页码：1758 / 1762

页数：5

共 50 条

[21] MULTI-SPEAKER, NARROWBAND, CONTINUOUS MARATHI SPEECH DATABASE
Godambe, Tejas
Bondale, Nandini
Samudravijaya, K.
Rao, Preeti
[J]. 2013 INTERNATIONAL CONFERENCE ORIENTAL COCOSDA HELD JOINTLY WITH 2013 CONFERENCE ON ASIAN SPOKEN LANGUAGE RESEARCH AND EVALUATION (O-COCOSDA/CASLRE), 2013,
[22] Speech Recognition and Multi-Speaker Diarization of Long Conversations
Mao, Huanru Henry
Li, Shuyang
McAuley, Julian
Cottrell, Garrison W.
[J]. INTERSPEECH 2020, 2020, : 691 - 695
[23] Multi-speaker Emotional Text-to-speech Synthesizer
Cho, Sungjae
Lee, Soo-Young
[J]. INTERSPEECH 2021, 2021, : 2337 - 2338
[24] Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes
Mitsui, Kentaro
Koriyama, Tomoki
Saruwatari, Hiroshi
[J]. INTERSPEECH 2020, 2020, : 2032 - 2036
[25] MULTI-SPEAKER EMOTIONAL SPEECH SYNTHESIS WITH FINE-GRAINED PROSODY MODELING
Lu, Chunhui
Wen, Xue
Liu, Ruolan
Chen, Xiao
[J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 5729 - 5733
[26] GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis
Yang, Jinhyeok
Bae, Jae-Sung
Bak, Taejun
Kim, Young-Ik
Cho, Hoon-Young
[J]. INTERSPEECH 2021, 2021, : 2202 - 2206
[27] Autoregressive multi-speaker model in Chinese speech synthesis based on variational autoencoder
Hao, Xiaoyang
Zhang, Pengyuan
[J]. Shengxue Xuebao/Acta Acustica, 2022, 47 (03): : 405 - 416
[28] J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis
Takamichi, Shinnosuke
Nakata, Wataru
Tanji, Naoko
Saruwatari, Hiroshi
[J]. INTERSPEECH 2022, 2022, : 2358 - 2362
[29] MULTI-SPEAKER EMOTIONAL ACOUSTIC MODELING FOR CNN-BASED SPEECH SYNTHESIS
Choi, Heejin
Park, Sangjun
Park, Jinuk
Hahn, Minsoo
[J]. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 6950 - 6954
[30] J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis
Takamichi, Shinnosuke
Nakata, Wataru
Tanji, Naoko
Saruwatari, Hiroshi
[J]. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2022, 2022-September : 2358 - 2362

← 1 2 3 4 5 →