Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora

Hieu-Thi Luong, Xin Wang, Junichi Yamagishi, Nobuyuki Nishizawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies have shown that neural multi-speaker TTS model trained with a small amount data from multiple speakers combined can generate synthetic speech with better quality and stability than a speaker-dependent one. However when the amount of data from each speaker is highly unbalanced, the best approach to make use of the excessive data remains unknown. Our experiments showed that simply combining all available data from every speaker to train a multi-speaker model produces better than or at least similar performance to its speaker-dependent counterpart. Moreover by using an ensemble multi-speaker model, in which each subsystem is trained on a subset of available data, we can further improve the quality of the synthetic speech especially for underrepresented speakers whose training data is limited.

Original languageEnglish
Title of host publicationProceedings Interspeech 2019
PublisherInternational Speech Communication Association
Pages1303-1307
Number of pages5
DOIs
Publication statusPublished - 19 Sept 2019
EventInterspeech 2019 - Graz, Austria
Duration: 15 Sept 201919 Sept 2019
https://www.interspeech2019.org/

Publication series

Name
PublisherInternational Speech Communication Association
ISSN (Electronic)1990-9772

Conference

ConferenceInterspeech 2019
Country/TerritoryAustria
CityGraz
Period15/09/1919/09/19
Internet address

Keywords / Materials (for Non-textual outputs)

  • speech synthesis
  • multi-speaker modeling
  • imbalanced corpus
  • ensemble learning

Fingerprint

Dive into the research topics of 'Training Multi-Speaker Neural Text-to-Speech Systems using Speaker-Imbalanced Speech Corpora'. Together they form a unique fingerprint.

Cite this