Multilingual Multiaccented Multispeaker TTS with RADTTS

TL;DR

This paper introduces RADTTS, a multilingual, multiaccented multispeaker speech synthesis model that generates natural speech with accurate accents and speaker characteristics without needing bilingual training data.

Contribution

We propose a novel RADTTS-based model that explicitly controls accent, language, and speaker features, enabling high-quality multilingual speech synthesis without bilingual data.

Findings

Better retention of speaker voice and accent quality compared to baselines.

Effective control over accents across 7 different accents.

Fluent speech synthesis in multiple languages and accents.

Abstract

We work to create a multilingual speech synthesis system which can generate speech with the proper accent while retaining the characteristics of an individual voice. This is challenging to do because it is expensive to obtain bilingual training data in multiple languages, and the lack of such data results in strong correlations that entangle speaker, language, and accent, resulting in poor transfer capabilities. To overcome this, we present a multilingual, multiaccented, multispeaker speech synthesis model based on RADTTS with explicit control over accent, language, speaker and fine-grained $F_0$ and energy features. Our proposed model does not rely on bilingual training data. We demonstrate an ability to control synthesized accent for any speaker in an open-source dataset comprising of 7 accents. Human subjective evaluation demonstrates that our model can better retain a speaker's voice and accent quality than controlled baselines while synthesizing fluent speech in all target languages and accents in our dataset.