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

Kezek 模型将两人对话分割为独立的音轨

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-14 05:00

研究人员开发了 Kezek，这是一种新颖的模型，旨在将两人对话的单声道音频录音分割成单独的说话者音轨。该模型旨在保留原始长度和时间，确保重叠和简短的回复保留给原始说话者。据报道，Kezek 在保留简短回复和减少声道切换方面优于 pyannote 和 DialogueSidon 等现有流程，同时速度也显著更快。 AI

影响该模型可以提高用于训练 AI 系统的对话数据的质量和可用性。

排序理由该集群描述了一篇关于新颖音频处理模型的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇关于新颖音频处理模型的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Bagzhan Karl, Alizhan Karl · 2026-11-14 05:00

Kezek：将单声道两人对话拆分为每位说话者的音轨，用于全双工对话数据

arXiv:2611.16933v1 Announce Type: cross 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…

本文如何被排名

报道来源 [1]

Kezek：将单声道两人对话拆分为每位说话者的音轨，用于全双工对话数据

相关实体

相关话题