Acoustic Modeling for End-to-End Empathetic Dialogue Speech Synthesis Using Linguistic and Prosodic Contexts of Dialogue History

TL;DR

This paper introduces an end-to-end empathetic dialogue speech synthesis model that incorporates linguistic and prosodic dialogue history, utilizing style-guided training and sentence-wise embeddings to improve speech quality in empathetic systems.

Contribution

It presents a novel empathetic DSS model that integrates dialogue history with style-guided training and sentence-level prosody modeling, advancing prior linguistic-feature-based approaches.

Findings

Prosodic context alone does not improve speech quality.

Style-guided training enhances speech naturalness.

Sentence-wise embedding improves prosody modeling accuracy.

Abstract

We propose an end-to-end empathetic dialogue speech synthesis (DSS) model that considers both the linguistic and prosodic contexts of dialogue history. Empathy is the active attempt by humans to get inside the interlocutor in dialogue, and empathetic DSS is a technology to implement this act in spoken dialogue systems. Our model is conditioned by the history of linguistic and prosody features for predicting appropriate dialogue context. As such, it can be regarded as an extension of the conventional linguistic-feature-based dialogue history modeling. To train the empathetic DSS model effectively, we investigate 1) a self-supervised learning model pretrained with large speech corpora, 2) a style-guided training using a prosody embedding of the current utterance to be predicted by the dialogue context embedding, 3) a cross-modal attention to combine text and speech modalities, and 4) a sentence-wise embedding to achieve fine-grained prosody modeling rather than utterance-wise modeling. The evaluation results demonstrate that 1) simply considering prosodic contexts of the dialogue history does not improve the quality of speech in empathetic DSS and 2) introducing style-guided training and sentence-wise embedding modeling achieves higher speech quality than that by the conventional method.