Prosodic Prominence and Boundaries in Sequence-to-Sequence Speech Synthesis

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

Abstract

Recent advances in deep learning methods have elevated synthetic speech quality to human level, and the field is now moving towards addressing prosodic variation in synthetic speech.Despite successes in this effort, the state-of-the-art systems fall short of faithfully reproducing local prosodic events that give rise to, e.g., word-level emphasis and phrasal structure. This type of prosodic variation often reflects long-distance semantic relationships that are not accessible for end-to-end systems with a single sentence as their synthesis domain. One of the possible solutions might be conditioning the synthesized speech by explicit prosodic labels, potentially generated using longer portions of text. In this work we evaluate whether augmenting the textual input with such prosodic labels capturing word-level prominence and phrasal boundary strength can result in more accurate realization of sentence prosody. We use an automatic wavelet-based technique to extract such labels from speech material, and use them as an input to a tacotron-like synthesis system alongside textual information. The results of objective evaluation of synthesized speech show that using the prosodic labels significantly improves the output in terms of faithfulness of f0 and energy contours, in comparison with state-of-the-art implementations.
Original languageEnglish
Title of host publicationProceedings of 10th International Conference on Speech Prosody 2020 : Communicative and Interactive Prosody
Number of pages5
Place of PublicationBaixas
PublisherISCA
Publication date2020
Pages940-944
DOIs
Publication statusPublished - 2020
MoE publication typeA4 Article in conference proceedings
EventThe 10th International Conference on Speech Prosody: Communicative and Interactive Prosody - Tokyo, Japan
Duration: 25 May 202028 May 2020
Conference number: 10
http://10.21437/SpeechProsody.2020

Publication series

NameSpeech prosody
PublisherInternational Speech Communication Association
ISSN (Electronic)2333-2042

Fields of Science

  • 6161 Phonetics
  • 6121 Languages

Cite this