Title | ||
---|---|---|
In Other News: A Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data. |
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. |
Year | Venue | DocType |
---|---|---|
2019 | North American Chapter of the Association for Computational Linguistics | Conference |
Volume | Citations | PageRank |
abs/1904.02790 | 0 | 0.34 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nishant Prateek | 1 | 0 | 0.34 |
Mateusz Lajszczak | 2 | 0 | 0.34 |
Roberto Barra-Chicote | 3 | 129 | 17.35 |
Thomas Drugman | 4 | 526 | 41.79 |
Jaime Lorenzo-Trueba | 5 | 46 | 9.26 |
Thomas Merritt | 6 | 18 | 5.81 |
Srikanth Ronanki | 7 | 2 | 2.10 |
Trevor Wood | 8 | 0 | 0.68 |