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

Show full item record



Permalink

http://hdl.handle.net/10138/318782

Citation

Suni , A , Kakouros , S , Vainio , M & Šimko , J 2020 , Prosodic Prominence and Boundaries in Sequence-to-Sequence Speech Synthesis . in Proceedings of 10th International Conference on Speech Prosody 2020 : Communicative and Interactive Prosody . Speech prosody , ISCA , Baixas , pp. 940-944 , The 10th International Conference on Speech Prosody , Tokyo , Japan , 25/05/2020 . https://doi.org/10.21437/SpeechProsody.2020-192

Title: Prosodic Prominence and Boundaries in Sequence-to-Sequence Speech Synthesis
Author: Suni, Antti; Kakouros, Sofoklis; Vainio, Martti; Šimko, Juraj
Other contributor: University of Helsinki, Phonetics
University of Helsinki, Department of Digital Humanities
University of Helsinki, Phonetics
University of Helsinki, Phonetics



Publisher: ISCA
Date: 2020
Language: eng
Number of pages: 5
Belongs to series: Proceedings of 10th International Conference on Speech Prosody 2020 Communicative and Interactive Prosody
Belongs to series: Speech prosody
DOI: https://doi.org/10.21437/SpeechProsody.2020-192
URI: http://hdl.handle.net/10138/318782
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.
Subject: 6161 Phonetics
6121 Languages
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
87.pdf 812.5Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record