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.

arXiv commentAccepted at NAACL-HLT 2019

References in corpus (8)

• Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
• Neural Voice Cloning with a Few Samples
• Evaluation of sentence embeddings in downstream and linguistic probing tasks
• Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
• Hierarchical Generative Modeling for Controllable Speech Synthesis
• Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder
• Predicting Expressive Speaking Style From Text In End-To-End Speech Synthesis
• Speaking style adaptation in Text-To-Speech synthesis using Sequence-to-sequence models with attention