%0 Conference Proceedings %T In Other News: a Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data %A Prateek, Nishant %A Łajszczak, Mateusz %A Barra-Chicote, Roberto %A Drugman, Thomas %A Lorenzo-Trueba, Jaime %A Merritt, Thomas %A Ronanki, Srikanth %A Wood, Trevor %Y Loukina, Anastassia %Y Morales, Michelle %Y Kumar, Rohit %S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers) %D 2019 %8 June %I Association for Computational Linguistics %C Minneapolis, Minnesota %F prateek-etal-2019-news %X 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. %R 10.18653/v1/N19-2026 %U https://aclanthology.org/N19-2026 %U https://doi.org/10.18653/v1/N19-2026 %P 205-213