Summary of Let’s Go Real Talk: Spoken Dialogue Model For Face-to-face Conversation, by Se Jin Park et al.
Let’s Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation
by Se Jin Park, Chae Won Kim, Hyeongseop Rha, Minsu Kim, Joanna Hong, Jeong Hun Yeo, Yong Man Ro
First submitted to arxiv on: 12 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The novel Face-to-Face spoken dialogue model introduced in this paper processes audio-visual speech from user input and generates audio-visual speech as the response, marking a significant step towards creating an avatar chatbot system without relying on intermediate text. The model incorporates a textually pretrained large language model and adapts it into the audio-visual spoken dialogue domain by incorporating speech-text joint pretraining. The paper also introduces MultiDialog, a large-scale multimodal 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 are expected to open up research opportunities in multimodal synthesis. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper introduces a new way for computers to have conversations using both sound and pictures. The model takes in what people say and see, and generates a response that includes both sound and images. This is an important step towards creating chatbots that can talk and interact with people like they would with each other. To test the model, the researchers created a large collection of audio-visual dialogues, which they hope will help others study how to make more realistic conversations. |
Keywords
» Artificial intelligence » Large language model » Pretraining
