English(EN) Audio-Visual Turn-taking Prediction in Cocktail Party Scenarios

视听轮流模型在嘈杂对话中表现不佳

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-16 04:00

研究人员评估了用于在嘈杂环境中（特别是鸡尾酒会场景）预测对话轮流的视听模型。研究发现，在干净数据上训练的模型在暴露于重叠语音和背景干扰时，性能显著下降。虽然微调提高了鲁棒性，但收益因模态和预训练数据的量而异，这凸显了音频和视觉线索在适应复杂人类互动方面的差异。 AI

影响强调了将AI模型应用于现实世界嘈杂对话数据的挑战，表明需要更鲁棒的适应策略。

排序理由该项目是一篇在arXiv上发表的研究论文，详细介绍了视听模型的实验。[lever_c_demoted from research: ic=1 ai=1.0]

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: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇在arXiv上发表的研究论文，详细介绍了视听模型的实验。[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。

arXiv cs.CL TIER_1 English(EN) · Long-Vu Hoang, Naomi Harte · 2026-09-16 04:00

鸡尾酒会场景中的视听轮流预测

arXiv:2609.17056v1 Announce Type: cross Abstract: Current predictive turn-taking models (PTTMs) achieve strong performance on benchmarks with controlled acoustic conditions and clean audio signals. Their generalisation to conversations with overlapping speech and background inter…