In Other News: a Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data

Nishant Prateek, Mateusz Łajszczak, Roberto Barra-Chicote, Thomas Drugman, Jaime Lorenzo-Trueba, Thomas Merritt, Srikanth Ronanki, Trevor Wood

Abstract
Neural text-to-speech synthesis (NTTS) models have shown significant progress in generating high-quality speech, however they require a large quantity of training data. This makes creating models for multiple styles expensive and time-consuming. In this paper different styles of speech are analysed based on prosodic variations, from this a model is proposed to synthesise speech in the style of a newscaster, with just a few hours of supplementary data. We pose the problem of synthesising in a target style using limited data as that of creating a bi-style model that can synthesise both neutral-style and newscaster-style speech via a one-hot vector which factorises the two styles. We also propose conditioning the model on contextual word embeddings, and extensively evaluate it against neutral NTTS, and neutral concatenative-based synthesis. This model closes the gap in perceived style-appropriateness between natural recordings for newscaster-style of speech, and neutral speech synthesis by approximately two-thirds.
Anthology ID:
N19-2026
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Anastassia Loukina, Michelle Morales, Rohit Kumar
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
205–213
Language:
URL:
https://aclanthology.org/N19-2026
DOI:
10.18653/v1/N19-2026
Bibkey:
Cite (ACL):
Nishant Prateek, Mateusz Łajszczak, Roberto Barra-Chicote, Thomas Drugman, Jaime Lorenzo-Trueba, Thomas Merritt, Srikanth Ronanki, and Trevor Wood. 2019. In Other News: a Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers), pages 205–213, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
In Other News: a Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data (Prateek et al., NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/N19-2026.pdf
PDF Search