Intel Labs 在 Ego4D Challenge 2022:更好的音视频日记化基线
Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization
AI总结:
本文针对 Ego4D Challenge 2022 的音视频日记化任务,通过改进训练方案、引入现成语音活动检测模型去除误报以及提升主动说话人检测性能,最终取得 65.9% DER 并获得第一名。
摘要:
本报告描述了我们针对 Ego4D Challenge 2022 中音视频日记化(Audio-Visual Diarization, AVD)任务所采用的方法。具体而言,我们在官方基线之上提出了多项技术改进。首先,我们通过修改相机佩戴者语音活动检测模型的训练方案,提升了其检测性能。其次,我们发现,当仅将现成的语音活动检测(voice activity detection)模型应用于相机佩戴者的语音活动时,可以有效去除误报。最后,我们表明更好的主动说话人检测(active speaker detection)能够带来更好的 AVD 结果。我们的最终方法在 Ego4D 测试集上取得了 65.9% 的 DER,显著优于所有基线。我们的提交方案在 Ego4D Challenge 2022 中获得了第一名。
英文摘要:
This report describes our approach for the Audio-Visual Diarization (AVD) task of the Ego4D Challenge 2022. Specifically, we present multiple technical improvements over the official baselines. First, we improve the detection performance of the camera wearer's voice activity by modifying the training scheme of its model. Second, we discover that an off-the-shelf voice activity detection model can effectively remove false positives when it is applied solely to the camera wearer's voice activities. Lastly, we show that better active speaker detection leads to a better AVD outcome. Our final method obtains 65.9% DER on the test set of Ego4D, which significantly outperforms all the baselines. Our submission achieved 1st place in the Ego4D Challenge 2022.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。