DCTTS: Discrete Diffusion Model with Contrastive Learning for Text-to-speech Generation

TL;DR

This paper introduces DCTTS, a discrete diffusion model with contrastive learning for text-to-speech synthesis, achieving high quality and fast sampling with reduced resource consumption.

Contribution

The paper presents a novel discrete diffusion model with contrastive learning and an efficient text encoder for improved TTS performance and efficiency.

Findings

High-quality speech synthesis demonstrated

Significant reduction in resource consumption

Faster sampling speed compared to traditional diffusion models

Abstract

In the Text-to-speech(TTS) task, the latent diffusion model has excellent fidelity and generalization, but its expensive resource consumption and slow inference speed have always been a challenging. This paper proposes Discrete Diffusion Model with Contrastive Learning for Text-to-Speech Generation(DCTTS). The following contributions are made by DCTTS: 1) The TTS diffusion model based on discrete space significantly lowers the computational consumption of the diffusion model and improves sampling speed; 2) The contrastive learning method based on discrete space is used to enhance the alignment connection between speech and text and improve sampling quality; and 3) It uses an efficient text encoder to simplify the model's parameters and increase computational efficiency. The experimental results demonstrate that the approach proposed in this paper has outstanding speech synthesis quality and sampling speed while significantly reducing the resource consumption of diffusion model. The synthesized samples are available at https://github.com/lawtherWu/DCTTS.