Kezek separates a mono two-speaker conversation into per-speaker tracks while preserving timing and short replies, using a phase-insensitive speaker-fingerprint-guided two-voice activity model followed by a conditioned time-domain separator, and it improves short-reply retention, leakage,…
Full-duplex spoken dialogue models learn turn-taking, overlaps and backchannels from conversations recorded with one channel per speaker, but most available conversational audio is a single mono mix. We present Kezek, a model that turns a mono recording of exactly two people into one track per person with the original length and timing; overlaps and short replies ("yeah", "mm-hm") stay on the track of the person who said them. Kezek decides who speaks when and who is who once for the whole recording (stage 1: a two-voice activity model guided by a speaker fingerprint trained to be insensitive to phase), and a conditioned time-domain separator only carries out that decision (stage 2), with…
full-duplex spoken dialogue modelsturn-takingoverlapsbackchannelsmono recordingtwo-voice activity modelspeaker fingerprintphase-insensitiveconditioned time-domain separatorshort-reply retention
- Upvotes
- 3
- Authors
- 2
- Published
- Nov 12, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.