Exploiting deep sentential context for expressive end-to-end speech synthesis

Fengyu Yang, Shan Yang, Qinghua Wu, Yujun Wang, Lei Xie

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

6 Scopus citations

Abstract

Attention-based seq2seq text-to-speech systems, especially those use self-attention networks (SAN), have achieved state-of-art performance. But an expressive corpus with rich prosody is still challenging to model as 1) prosodic aspects, which span across different sentential granularities and mainly determine acoustic expressiveness, are difficult to quantize and label and 2) the current seq2seq framework extracts prosodic information solely from a text encoder, which is easily collapsed to an averaged expression for expressive contents. In this paper, we propose a context extractor, which is built upon SAN-based text encoder, to sufficiently exploit the sentential context over an expressive corpus for seq2seq-based TTS. Our context extractor first collects prosodic-related sentential context information from different SAN layers and then aggregates them to learn a comprehensive sentence representation to enhance the expressiveness of the final generated speech. Specifically, we investigate two methods of context aggregation: 1) direct aggregation which directly concatenates the outputs of different SAN layers, and 2) weighted aggregation which uses multi-head attention to automatically learn contributions for different SAN layers. Experiments on two expressive corpora show that our approach can produce more natural speech with much richer prosodic variations, and weighted aggregation is more superior in modeling expressivity.

Original languageEnglish
Title of host publicationInterspeech 2020
PublisherInternational Speech Communication Association
Pages3436-3440
Number of pages5
ISBN (Print)9781713820697
DOIs
StatePublished - 2020
Event21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 - Shanghai, China
Duration: 25 Oct 202029 Oct 2020

Publication series

NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume2020-October
ISSN (Print)2308-457X
ISSN (Electronic)1990-9772

Conference

Conference21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020
Country/TerritoryChina
CityShanghai
Period25/10/2029/10/20

Keywords

  • IndexTerms: speech synthesis
  • Prosody
  • Self-attention network

Fingerprint

Dive into the research topics of 'Exploiting deep sentential context for expressive end-to-end speech synthesis'. Together they form a unique fingerprint.

Cite this