Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion

Autor:	Wang, Jinhan, Chen, Long, Khare, Aparna, Raju, Anirudh, Dheram, Pranav, He, Di, Wu, Minhua, Stolcke, Andreas, Ravichandran, Venkatesh
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Machine Learning Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	We propose an approach for continuous prediction of turn-taking and backchanneling locations in spoken dialogue by fusing a neural acoustic model with a large language model (LLM). Experiments on the Switchboard human-human conversation dataset demonstrate that our approach consistently outperforms the baseline models with single modality. We also develop a novel multi-task instruction fine-tuning strategy to further benefit from LLM-encoded knowledge for understanding the tasks and conversational contexts, leading to additional improvements. Our approach demonstrates the potential of combined LLMs and acoustic models for a more natural and conversational interaction between humans and speech-enabled AI agents. Comment: To appear in IEEE ICASSP 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2401.14717 Zobrazit plný text záznamu View this record from Arxiv