Debatts: Zero-Shot Debating Text-to-Speech Synthesis

TL;DR

Debatts is a novel zero-shot text-to-speech system designed for rebuttal in debating, capable of generating persuasive speech with appropriate style and identity from minimal prompts, trained on a new debating dataset.

Contribution

The paper introduces Debatts, a zero-shot TTS system specifically tailored for debating rebuttal, incorporating style and identity prompts, and trained on a newly created debating dataset.

Findings

Debatts outperforms classic zero-shot TTS systems in style and identity transfer.

The system effectively generates debating-style speech for any voice.

Experimental results validate the system's ability to produce persuasive rebuttal speech.

Abstract

In debating, rebuttal is one of the most critical stages, where a speaker addresses the arguments presented by the opposing side. During this process, the speaker synthesizes their own persuasive articulation given the context from the opposing side. This work proposes a novel zero-shot text-to-speech synthesis system for rebuttal, namely Debatts. Debatts takes two speech prompts, one from the opposing side (i.e. opponent) and one from the speaker. The prompt from the opponent is supposed to provide debating style prosody, and the prompt from the speaker provides identity information. In particular, we pretrain the Debatts system from in-the-wild dataset, and integrate an additional reference encoder to take debating prompt for style. In addition, we also create a debating dataset to develop Debatts. In this setting, Debatts can generate a debating-style speech in rebuttal for any voices. Experimental results confirm the effectiveness of the proposed system in comparison with the classic zero-shot TTS systems.