DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance

TL;DR

DualSpeech is a novel TTS model that uses phoneme-level latent diffusion and dual classifier-free guidance to achieve superior control over speaker-fidelity and text-intelligibility, surpassing existing models.

Contribution

It introduces a new TTS framework combining phoneme-level latent diffusion with dual classifier-free guidance for enhanced speech control.

Findings

Outperforms state-of-the-art TTS models in quality.

Provides exceptional control over speaker and text attributes.

Demonstrates significant improvements through experimental evaluation.

Abstract

Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despite these advancements, achieving an optimal balance between speaker-fidelity and text-intelligibility remains a challenge, particularly when diverse control demands are considered. Addressing this, we introduce DualSpeech, a TTS model that integrates phoneme-level latent diffusion with dual classifier-free guidance. This approach enables exceptional control over speaker-fidelity and text-intelligibility. Experimental results demonstrate that by utilizing the sophisticated control, DualSpeech surpasses existing state-of-the-art TTS models in performance. Demos are available at https://bit.ly/48Ewoib.