Extended EPIC-SOUND paper was accepted at TPAMI
arxiv.org/abs/2302.006...
This follows ICASSP 2023 oral, extended for detection and further analysis
epic-kitchens.github.io/epic-sounds/
work by @jaesunghuh.bsky.social Jacob Chalk @ekazakos.bsky.social
@oxford-vgg.bsky.social @bristoluni.bsky.social
📖 Advancing Active Speaker Detection for Egocentric Videos
This paper explores how to train robust Active Speaker Detection (ASD) model for egocentric videos.
Paper : ieeexplore.ieee.org/stamp/stamp....
Machine learning for multimodal data I (Poster)
Apr 11: 11:30 am - 1:00 pm
📖 The VoxCeleb Speaker Recognition Challenge: A Retrospective
This paper presents a review of the VoxCeleb Speaker Recognition Challenges (VoxSRC).
Paper : arxiv.org/abs/2408.14886
Speaker Recognition II (Poster)
Apr 9: 5:00 pm - 6:30 pm
Attending #ICASSP2025 next week at Hyderabad from April 7th. Ping me if you want to meet in person! 🤗
I'm presenting two papers ⬇️⬇️⬇️
VoxConverse has become one of the most widely-used speaker diarization evaluation datasets since 2020. Please also check out the paper and dataset below.
Code : github.com/JaesungHuh/a...
Paper : arxiv.org/abs/2007.01216
Dataset : mm.kaist.ac.kr/datasets/vox...
I'm releasing the audio-visual diarization pipeline that was used to create the VoxConverse dataset. Along with the original code, an enhanced version featuring new VAD and speaker verification models is now available.
VoxConverse has become one of the most widely-used speaker diarization evaluation datasets since 2020. Please also check out the paper and dataset below.
Code : github.com/JaesungHuh/a...
Paper : arxiv.org/abs/2007.01216
Since my PhD journey going towards the end (I’m currently looking for a full-time job in Research Engineer / Scientist positions!), I’m trying to open-source all the codes I’ve participated in! This is the first edition.
#VoxConverse #Speakerdiarization #Audiovisual
