Improving mandarin end-To-end speech synthesis by self-Attention and learnable gaussian bias

Fengyu Yang, Shan Yang, Pengcheng Zhu, Pengju Yan, Lei Xie

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

15 Scopus citations

Abstract

Compared to conventional speech synthesis, end-To-end speech synthesis has achieved much better naturalness with more simplified system building pipeline. End-To-end framework can generate natural speech directly from characters for English. But for other languages like Chinese, recent studies have indicated that extra engineering features are still needed for model robustness and naturalness, e.g, word boundaries and prosody boundaries, which makes the front-end pipeline as complicated as the traditional approach. To maintain the naturalness of generated speech and discard language-specific expertise as much as possible, in Mandarin TTS, we introduce a novel self-Attention based encoder with learnable Gaussian bias in Tacotron. We evaluate different systems with and without complex prosody information and results show that the proposed approach has the ability to generate stable and natural speech with minimum language-dependent front-end modules.

Original languageEnglish
Title of host publication2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages208-213
Number of pages6
ISBN (Electronic)9781728103068
DOIs
StatePublished - Dec 2019
Event2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Singapore, Singapore
Duration: 15 Dec 201918 Dec 2019

Publication series

Name2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019 - Proceedings

Conference

Conference2019 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2019
Country/TerritorySingapore
CitySingapore
Period15/12/1918/12/19

Keywords

  • end-To-end
  • Gaussian bias
  • self-Attention
  • speech synthesis
  • Tacotron

Fingerprint

Dive into the research topics of 'Improving mandarin end-To-end speech synthesis by self-Attention and learnable gaussian bias'. Together they form a unique fingerprint.

Cite this