Search papers, labs, and topics across Lattice.
The paper introduces CONCORD, a privacy-aware assistant-to-assistant framework that allows proactive speech-based AI to collaborate and recover missing context while protecting the privacy of non-consenting speakers. CONCORD uses real-time speaker verification to enforce owner-only speech capture, then recovers necessary context through spatio-temporal context resolution, information gap detection, and minimal A2A queries governed by relationship awareness. Experiments on a multi-domain dialogue dataset demonstrate CONCORD's effectiveness, achieving high recall in gap detection (91.4%), relationship classification accuracy (96%), and a high true negative rate in privacy-sensitive disclosure decisions (97%).
Always-listening AI doesn't have to be creepy: CONCORD shows how assistants can collaboratively fill in context gaps while respecting privacy boundaries.
We introduce CONCORD, a privacy-aware asynchronous assistant-to-assistant (A2A) framework that leverages collaboration between proactive speech-based AI. As agents evolve from reactive to always-listening assistants, they face a core privacy risk (of capturing non-consenting speakers), which makes their social deployment a challenge. To overcome this, we implement CONCORD, which enforces owner-only speech capture via real-time speaker verification, producing a one-sided transcript that incurs missing context but preserves privacy. We demonstrate that CONCORD can safely recover necessary context through (1) spatio-temporal context resolution, (2) information gap detection, and (3) minimal A2A queries governed by a relationship-aware disclosure. Instead of hallucination-prone inferring, CONCORD treats context recovery as a negotiated safe exchange between assistants. Across a multi-domain dialogue dataset, CONCORD achieves 91.4% recall in gap detection, 96% relationship classification accuracy, and 97% true negative rate in privacy-sensitive disclosure decisions. By reframing always-listening AI as a coordination problem between privacy-preserving agents, CONCORD offers a practical path toward socially deployable proactive conversational agents.
