ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings

TL;DR

This paper introduces ChatGPT-EDSS, a speech synthesis method that uses ChatGPT to extract context and emotion cues for empathetic dialogue speech generation, achieving comparable performance to label-based methods.

Contribution

It presents a novel approach that leverages ChatGPT-derived context embeddings for empathetic speech synthesis, bypassing the need for explicit emotion labels.

Findings

Performance comparable to emotion label-based methods

Effective use of ChatGPT-derived context embeddings

Available dataset of ChatGPT-derived context information

Abstract

We propose ChatGPT-EDSS, an empathetic dialogue speech synthesis (EDSS) method using ChatGPT for extracting dialogue context. ChatGPT is a chatbot that can deeply understand the content and purpose of an input prompt and appropriately respond to the user's request. We focus on ChatGPT's reading comprehension and introduce it to EDSS, a task of synthesizing speech that can empathize with the interlocutor's emotion. Our method first gives chat history to ChatGPT and asks it to generate three words representing the intention, emotion, and speaking style for each line in the chat. Then, it trains an EDSS model using the embeddings of ChatGPT-derived context words as the conditioning features. The experimental results demonstrate that our method performs comparably to ones using emotion labels or neural network-derived context embeddings learned from chat histories. The collected ChatGPT-derived context information is available at https://sarulab-speech.github.io/demo_ChatGPT_EDSS/.