paper-with-me

Papers

Multi-Task Learning for Audio Visual Active Speaker Detection

2019-06-01 · The ActivityNet Large-Scale Activity Recognition Challenge Workshop, CVPR 2019 6 · Yuanhang Zhang, Jingyun Xiao, Shuang Yang, Shiguang Shan

This report describes the approach underlying our submission to the active speaker detection task (task B-2) of ActivityNet Challenge 2019. We introduce a new audio-visual model which builds upon a 3D-ResNet18 visual model pretrained for lipreading and a VGG-M acoustic model pretrained for audio-to-video synchronization. The model is trained with two losses in a multi-task learning fashion: a contrastive loss to enforce matching between audio and video features for active speakers, and a regular crossentropy loss to obtain speaker / non-speaker labels. This model obtains 84.0% mAP on the validation set of AVAActiveSpeaker. Experimental results showcase the pretrained embeddings' abilities to transfer across tasks and data formats, as well as the advantage of the proposed multi-task learning strategy.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Active Speaker DetectionAudio-Visual Active Speaker DetectionLipreadingMulti-Task LearningVideo Synchronization

Similar Papers 제목 키워드 기반

Look\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement

2022-03-04 · Junwen Xiong, Yu Zhou, Peng Zhang, Lei Xie 외

Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding. According to their respective characteristics, the scheme of independently designed a…

Active Speaker DetectionMulti-Task LearningSpeech Enhancement

Active Speakers in Context

2020-05-20 · CVPR 2020 6 · Juan Leon Alcazar, Fabian Caba Heilbron, Long Mai, Federico Perazzi 외

Current methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker. Although this strategy can be enough for addressing single-speaker scenarios, it prevents accurate…

Active Speaker DetectionAudio-Visual Active Speaker Detection

AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection

2019-01-05 · Joseph Roth, Sourish Chaudhuri, Ondrej Klejch, Radhika Marvin 외

Active speaker detection is an important component in video analysis algorithms for applications such as speaker diarization, video re-targeting for meetings, speech enhancement, and human-robot interaction. The absence …

Active Speaker DetectionAudio-Visual Active Speaker DetectionDiversityspeaker-diarization+2

Leveraging Visual Supervision for Array-based Active Speaker Detection and Localization

2023-12-21 · Davide Berghi, Philip J. B. Jackson

Conventional audio-visual approaches for active speaker detection (ASD) typically rely on visually pre-extracted face tracks and the corresponding single-channel audio to find the speaker in a video. Therefore, they tend…

Active Speaker DetectionSelf-Supervised Learning

Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function

2022-10-26 · Qing Wang, Hang Chen, Ya Jiang, Zhe Wang 외

In this paper, we propose a deep learning based multi-speaker direction of arrival (DOA) estimation with audio and visual signals by using permutation-free loss function. We first collect a data set for multi-modal sound…

Active Speaker DetectionSound Source Localization