Kezek：将单声道双人对话拆分为按说话人分轨，用于全双工对话数据
Kezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue Data
AI 导读
arXiv 论文提出 Kezek 模型，可将两人的单声道录音拆分为每人一条、保持原始时长与时序的分轨，供全双工口语对话模型训练使用。
正文 · 原文
Abstract: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 outputs that always sum to the input. Standard separation metrics miss the failures that matter for dialogue data, so we report short-reply retention, leakage onto the other person's solo, channel swaps and coverage. Against the open pipeline pyannote -> DialogueSidon on the same recordings, Kezek keeps more short replies (0.83 vs. 0.69 on Open Yap test; 0.80 vs. 0.71 over the other's speech on unseen telephone speech from CallHome English), mostly because it returns the whole recording while the external pipeline drops part of it (on the audio both return, reply retention is about the same: 0.859 vs. 0.865 on Open Yap); it also leaks less, swaps channels less often, and runs 4-5 times faster (about 230 hours of audio per GPU-hour). We also report negative results and an ideal-mask ceiling that locate the remaining gap: quiet replies under a louder voice. Code and weights are released under permissive licences.
| Comments: | 18 pages, 15 tables, 2 figures. Code: this https URL ; weights: this https URL ; listening examples: this https URL |
| Subjects: | Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.16933 [eess.AS] |
| (or arXiv:2611.16933v1 [eess.AS] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16933 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Bagzhan Karl [view email]
[v1]
Thu, 12 Nov 2026 15:19:35 UTC (67 KB)
来源：arXiv cs.AI · arxiv.org