Multi-Scale Accent Modeling and Disentangling for Multi-Speaker Multi-Accent Text-to-Speech Synthesis

TL;DR

This paper introduces a multi-scale accent modeling approach for multi-speaker, multi-accent TTS that disentangles speaker and accent features, enabling high-quality, accent-specific speech synthesis.

Contribution

It proposes a novel multi-scale accent modeling framework with global and local accent representations and a speaker disentanglement strategy for independent accent control.

Findings

Outperforms baseline systems in speech quality and accent rendering.

Effective multi-scale accent modeling captures both global and phoneme-level variations.

Speaker disentanglement enables independent control of speaker identity and accent.

Abstract

Generating speech across different accents while preserving speaker identity is crucial for various real-world applications. However, accurately and independently modeling both speaker and accent characteristics in text-to-speech (TTS) systems is challenging due to the complex variations of accents and the inherent entanglement between speaker and accent identities. In this paper, we propose a novel approach for multi-speaker multi-accent TTS synthesis that aims to synthesize speech for multiple speakers, each with various accents. Our approach employs a multi-scale accent modeling strategy to address accent variations on different levels. Specifically, we introduce both global (utterance level) and local (phoneme level) accent modeling to capture overall accent characteristics within an utterance and fine-grained accent variations across phonemes, respectively. To enable independent control of speakers and accents, we use the speaker embedding to represent speaker identity and achieve speaker-independent accent control through speaker disentanglement within the multi-scale accent modeling. Additionally, we present a local accent prediction model that enables our system to generate accented speech directly from phoneme inputs. We conduct extensive experiments on an English accented speech corpus. Experimental results demonstrate that our proposed system outperforms baseline systems in terms of speech quality and accent rendering for generating multi-speaker multi-accent speech. Ablation studies further validate the effectiveness of different components in our proposed system.