Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding

TL;DR

This paper introduces three progressive diffusion-based models for minimally-supervised speech synthesis, addressing key issues in semantic coding and prosody modeling to improve audio quality and diversity.

Contribution

It proposes Diff-LM-Speech, Tetra-Diff-Speech, and Tri-Diff-Speech, novel diffusion-based architectures that enhance semantic encoding and prosody control in TTS with minimal supervision.

Findings

Proposed models outperform baseline methods in quality.

Diffusion models improve semantic embedding accuracy.

Non-autoregressive structures enable diverse prosodic expressions.

Abstract

Recently, there has been a growing interest in text-to-speech (TTS) methods that can be trained with minimal supervision by combining two types of discrete speech representations and using two sequence-to-sequence tasks to decouple TTS. However, existing methods suffer from three problems: the high dimensionality and waveform distortion of discrete speech representations, the prosodic averaging problem caused by the duration prediction model in non-autoregressive frameworks, and the information redundancy and dimension explosion problems of existing semantic encoding methods. To address these problems, three progressive methods are proposed. First, we propose Diff-LM-Speech, an autoregressive structure consisting of a language model and diffusion models, which models the semantic embedding into the mel-spectrogram based on a diffusion model to achieve higher audio quality. We also introduce a prompt encoder structure based on a variational autoencoder and a prosody bottleneck to improve prompt representation ability. Second, we propose Tetra-Diff-Speech, a non-autoregressive structure consisting of four diffusion model-based modules that design a duration diffusion model to achieve diverse prosodic expressions. Finally, we propose Tri-Diff-Speech, a non-autoregressive structure consisting of three diffusion model-based modules that verify the non-necessity of existing semantic encoding models and achieve the best results. Experimental results show that our proposed methods outperform baseline methods. We provide a website with audio samples.