An unsupervised method to select a speaker subset from large multi-speaker speech synthesis datasets

Gallegos, Pilar Oplustil, Williams, Jennifer, Rownicka, Joanna and King, Simon (2020) An unsupervised method to select a speaker subset from large multi-speaker speech synthesis datasets. Proceedings of the Annual Conference of the International Speech Communication Association: INTERSPEECH 2020, Shanghai, Shanghai, China. 25 Oct 2020 - 29 Oct 2022 . 1758 pp .

Record type: Conference or Workshop Item (Paper)

Abstract

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.

This record has no associated files available for download.

More information

Published date: 31 October 2020

Additional Information: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, ISSN (Print)2308-457X

Venue - Dates: Proceedings of the Annual Conference of the International Speech Communication Association: INTERSPEECH 2020, Shanghai, Shanghai, China, 2020-10-25 - 2022-10-29

Related URLs:

Learn more about Agents, Interactions and Complexity research