DS-TTS: Zero-Shot Speaker Style Adaptation from Voice Clips via Dynamic Dual-Style Feature Modulation

TL;DR

This paper introduces DS-TTS, a novel zero-shot TTS system that uses dual-style encoding and dynamic adaptation to synthesize natural, expressive speech for unseen speakers from minimal voice samples.

Contribution

We propose DS-TTS with a Dual-Style Encoding Network and Style Gating-Film mechanism, advancing zero-shot voice cloning by better capturing speaker style and handling variable sentence lengths.

Findings

Outperforms existing models in word error rate and speaker similarity

Demonstrates robust generalization to unseen speakers

Improves naturalness and expressiveness of synthesized speech

Abstract

Recent advancements in text-to-speech (TTS) technology have increased demand for personalized audio synthesis. Zero-shot voice cloning, a specialized TTS task, aims to synthesize a target speaker's voice using only a single audio sample and arbitrary text, without prior exposure to the speaker during training. This process employs pattern recognition techniques to analyze and replicate the speaker's unique vocal features. Despite progress, challenges remain in adapting to the vocal style of unseen speakers, highlighting difficulties in generalizing TTS systems to handle diverse voices while maintaining naturalness, expressiveness, and speaker fidelity. To address the challenges of unseen speaker style adaptation, we propose DS-TTS, a novel approach aimed at enhancing the synthesis of diverse, previously unheard voices. Central to our method is a Dual-Style Encoding Network (DuSEN), where two distinct style encoders capture complementary aspects of a speaker's vocal identity. These speaker-specific style vectors are seamlessly integrated into the Dynamic Generator Network (DyGN) via a Style Gating-Film (SGF) mechanism, enabling more accurate and expressive reproduction of unseen speakers' unique vocal characteristics. In addition, we introduce a Dynamic Generator Network to tackle synthesis issues that arise with varying sentence lengths. By dynamically adapting to the length of the input, this component ensures robust performance across diverse text inputs and speaker styles, significantly improving the model's ability to generalize to unseen speakers in a more natural and expressive manner. Experimental evaluations on the VCTK dataset suggest that DS-TTS demonstrates superior overall performance in voice cloning tasks compared to existing state-of-the-art models, showing notable improvements in both word error rate and speaker similarity.