Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation

TL;DR

This paper presents a novel face-to-face spoken dialogue model that generates audio-visual responses directly from multimodal input, advancing avatar chatbot technology without intermediate text, supported by a large-scale multimodal dialogue dataset.

Contribution

Introduces MultiDialog, the first large-scale multimodal dialogue corpus, and develops a face-to-face spoken dialogue model integrating large language models with speech-text pretraining.

Findings

Model effectively facilitates face-to-face conversations.

MultiDialog dataset enables multimodal synthesis research.

Demonstrates the feasibility of audio-visual dialogue generation.

Abstract

In this paper, we introduce a novel Face-to-Face spoken dialogue model. It processes audio-visual speech from user input and generates audio-visual speech as the response, marking the initial step towards creating an avatar chatbot system without relying on intermediate text. To this end, we newly introduce MultiDialog, the first large-scale multimodal (i.e., audio and visual) spoken dialogue corpus containing 340 hours of approximately 9,000 dialogues, recorded based on the open domain dialogue dataset, TopicalChat. The MultiDialog contains parallel audio-visual recordings of conversation partners acting according to the given script with emotion annotations, which we expect to open up research opportunities in multimodal synthesis. Our Face-to-Face spoken dialogue model incorporates a textually pretrained large language model and adapts it into the audio-visual spoken dialogue domain by incorporating speech-text joint pretraining. Through extensive experiments, we validate the effectiveness of our model in facilitating a face-to-face conversation. Demo and data are available at https://multidialog.github.io and https://huggingface.co/datasets/IVLLab/MultiDialog, respectively.