EgoSpeak: Learning When to Speak for Egocentric Conversational Agents in the Wild
This addresses the challenge of enabling human-like interactions for conversational agents in complex, untrimmed video settings, though it appears incremental as it builds on existing datasets and baseline comparisons.
The paper tackles the problem of predicting when to initiate speech for conversational agents in real-world environments, introducing EgoSpeak, a framework that outperforms random and silence-based baselines on datasets like EasyCom and Ego4D.
Predicting when to initiate speech in real-world environments remains a fundamental challenge for conversational agents. We introduce EgoSpeak, a novel framework for real-time speech initiation prediction in egocentric streaming video. By modeling the conversation from the speaker's first-person viewpoint, EgoSpeak is tailored for human-like interactions in which a conversational agent must continuously observe its environment and dynamically decide when to talk. Our approach bridges the gap between simplified experimental setups and complex natural conversations by integrating four key capabilities: (1) first-person perspective, (2) RGB processing, (3) online processing, and (4) untrimmed video processing. We also present YT-Conversation, a diverse collection of in-the-wild conversational videos from YouTube, as a resource for large-scale pretraining. Experiments on EasyCom and Ego4D demonstrate that EgoSpeak outperforms random and silence-based baselines in real time. Our results also highlight the importance of multimodal input and context length in effectively deciding when to speak.