Trendoday

Kezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue Data

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.

  • Upvotes3
–Rank now
#25Peak rank
2Days on list
36Score · 7d
Nov 19, 2026First seen
Rank · 7 days

About this paper

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.

Trending history

Kezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue Data was first seen on Hugging Face · Daily papers on Nov 19, 2026. Since then it has appeared in 8 checks on 2 different days. Its best position was #25 of 30, reached on Nov 20, 05:29 UTC. It dropped off the list after Nov 20, 13:29 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 15:2920:5902:2907:5913:29 Nov 19, 15:29 UTC · #27Nov 20, 01:29 UTC · #27Nov 20, 03:29 UTC · #26Nov 20, 05:29 UTC · #25Nov 20, 07:29 UTC · #28Nov 20, 09:29 UTC · #28Nov 20, 11:29 UTC · #29Nov 20, 13:29 UTC · #30

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

0257 15:2920:5902:2907:5913:29 Nov 19, 15:29 UTC · 3Nov 20, 01:29 UTC · 5Nov 20, 03:29 UTC · 6Nov 20, 05:29 UTC · 6Nov 20, 07:29 UTC · 6Nov 20, 09:29 UTC · 6Nov 20, 11:29 UTC · 6Nov 20, 13:29 UTC · 7

Questions

Is Kezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue Data trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 20, 13:29 UTC, after 2 days of trending.

What is the highest rank Kezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue Data reached?

#25 on Hugging Face · Daily papers, on Nov 20, 05:29 UTC. Trendoday checks this list every 120 minutes.

How long has Kezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue Data been trending?

It was first seen on Nov 19, 2026 and has been on the list on 2 days (8 checks) since.