PromptTTS++: Controlling Speaker Identity in Prompt-Based Text-to-Speech Using Natural Language Descriptions

TL;DR

PromptTTS++ introduces a novel prompt-based TTS system that enables flexible control over speaker identity through natural language descriptions, leveraging a new dataset and diffusion-based modeling for improved speaker characteristic manipulation.

Contribution

It presents a new speaker prompt concept and a dataset for training, enabling natural language control of speaker identity in TTS, which surpasses previous style-based methods.

Findings

Better control of speaker characteristics demonstrated in subjective evaluations.

Effective mapping from natural language descriptions to diverse speaker features.

Utilization of a diffusion-based acoustic model improves speaker diversity handling.

Abstract

We propose PromptTTS++, a prompt-based text-to-speech (TTS) synthesis system that allows control over speaker identity using natural language descriptions. To control speaker identity within the prompt-based TTS framework, we introduce the concept of speaker prompt, which describes voice characteristics (e.g., gender-neutral, young, old, and muffled) designed to be approximately independent of speaking style. Since there is no large-scale dataset containing speaker prompts, we first construct a dataset based on the LibriTTS-R corpus with manually annotated speaker prompts. We then employ a diffusion-based acoustic model with mixture density networks to model diverse speaker factors in the training data. Unlike previous studies that rely on style prompts describing only a limited aspect of speaker individuality, such as pitch, speaking speed, and energy, our method utilizes an additional speaker prompt to effectively learn the mapping from natural language descriptions to the acoustic features of diverse speakers. Our subjective evaluation results show that the proposed method can better control speaker characteristics than the methods without the speaker prompt. Audio samples are available at https://reppy4620.github.io/demo.promptttspp/.