FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis
Year: 2024
Type: conference-paper
Abstract: Conversational Text-to-Speech (TTS) aims to synthesis an utterance with the right linguistic and affective prosody in a conversational context. The correlation between the current utterance and the dialogue history at the utterance level was used to improve the expressiveness of synthesized speech. However, the fine-grained information in the dialogue history at the word level also has an important impact on the prosodic expression of an utterance, which has not been well studied in the prior work. Therefore, we propose a novel expressive conversational TTS model, termed as FCTalker, that learns the fine and coarse grained context dependency at the same time during speech generation. Specifically, the FCTalker includes fine and coarse grained encoders to exploit the word and utterance-level context dependency. To model the word-level dependencies between an utterance and its dialogue history, the fine-grained dialogue encoder is built on top of a dialogue BERT model. The subjective and objective evaluation results show that the proposed model achieves remarkable results compared to the baseline model and generates contextually appropriate expressive speech. We release the source code at: https://github.com/AI-S2-Lab/FCTalker.
Authors: Yifan Hu, Rui Liu, Guanglai Gao, Haizhou Li
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G600008135
OpenAlex ID: W4405710078