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.
@article{arxiv.2408.14423,
title = {DualSpeech: Enhancing Speaker-Fidelity and Text-Intelligibility Through Dual Classifier-Free Guidance},
author = {Jinhyeok Yang and Junhyeok Lee and Hyeong-Seok Choi and Seunghun Ji and Hyeongju Kim and Juheon Lee},
journal= {arXiv preprint arXiv:2408.14423},
year = {2024}
}