TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models

TL;DR

This paper introduces TextrolSpeech, a large-scale dataset with natural text style prompts for controllable TTS, and proposes Salle, an architecture that uses codec codes for diverse style speech generation, advancing natural text-driven speech synthesis.

Contribution

The paper presents the first large-scale dataset with natural text style prompts and introduces Salle, a novel architecture that enhances style diversity in controllable TTS using codec codes.

Findings

TextrolSpeech contains 236,220 style prompt-speech pairs.

Salle achieves comparable performance to traditional models in controllable TTS.

The multi-stage prompt programming effectively utilizes GPT for style description generation.

Abstract

Recently, there has been a growing interest in the field of controllable Text-to-Speech (TTS). While previous studies have relied on users providing specific style factor values based on acoustic knowledge or selecting reference speeches that meet certain requirements, generating speech solely from natural text prompts has emerged as a new challenge for researchers. This challenge arises due to the scarcity of high-quality speech datasets with natural text style prompt and the absence of advanced text-controllable TTS models. In light of this, 1) we propose TextrolSpeech, which is the first large-scale speech emotion dataset annotated with rich text attributes. The dataset comprises 236,220 pairs of style prompt in natural text descriptions with five style factors and corresponding speech samples. Through iterative experimentation, we introduce a multi-stage prompt programming approach that effectively utilizes the GPT model for generating natural style descriptions in large volumes. 2) Furthermore, to address the need for generating audio with greater style diversity, we propose an efficient architecture called Salle. This architecture treats text controllable TTS as a language model task, utilizing audio codec codes as an intermediate representation to replace the conventional mel-spectrogram. Finally, we successfully demonstrate the ability of the proposed model by showing a comparable performance in the controllable TTS task. Audio samples are available at https://sall-e.github.io/