399 citations · 903 across the 21 of their papers we have counts for
24 papers
Character-aware audio-visual subtitling in context
Jaesung Huh, Andrew Zisserman
This paper presents an improved framework for character-aware audio-visual subtitling in TV shows. Our approach integrates speech recognition, speaker diarisation, and character re…
The VoxCeleb Speaker Recognition Challenge: A Retrospective
Jaesung Huh, Joon Son Chung, Arsha Nagrani +4
The VoxCeleb Speaker Recognition Challenges (VoxSRC) were a series of challenges and workshops that ran annually from 2019 to 2023. The challenges primarily evaluated the tasks of…
TIM: A Time Interval Machine for Audio-Visual Action Recognition
Jacob Chalk, Jaesung Huh, Evangelos Kazakos +2
Diverse actions give rise to rich audio-visual signals in long videos. Recent works showcase that the two modalities of audio and video exhibit different temporal extents of events…
Look, Listen and Recognise: Character-Aware Audio-Visual Subtitling
Bruno Korbar, Jaesung Huh, Andrew Zisserman
The goal of this paper is automatic character-aware subtitle generation. Given a video and a minimal amount of metadata, we propose an audio-visual method that generates a full tra…
OxfordVGG Submission to the EGO4D AV Transcription Challenge
Jaesung Huh, Max Bain, Andrew Zisserman
This report presents the technical details of our submission on the EGO4D Audio-Visual (AV) Automatic Speech Recognition Challenge 2023 from the OxfordVGG team. We present WhisperX…
VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge
Jaesung Huh, Andrew Brown, Jee-weon Jung +4
This paper summarises the findings from the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22), which was held in conjunction with INTERSPEECH 2022. The goal of this challenge…
WhisperX: Time-Accurate Speech Transcription of Long-Form Audio
Max Bain, Jaesung Huh, Tengda Han +1
Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages. However, their a…
Epic-Sounds: A Large-scale Dataset of Actions That Sound
Jaesung Huh, Jacob Chalk, Evangelos Kazakos +2
We introduce EPIC-SOUNDS, a large-scale dataset of audio annotations capturing temporal extents and class labels within the audio stream of the egocentric videos. We propose an ann…
Disentangled representation learning for multilingual speaker recognition
Kihyun Nam, Youkyum Kim, Jaesung Huh +3
The goal of this paper is to learn robust speaker representation for bilingual speaking scenario. The majority of the world's population speak at least two languages; however, most…
In search of strong embedding extractors for speaker diarisation
Jee-weon Jung, Hee-Soo Heo, Bong-Jin Lee +5
Speaker embedding extractors (EEs), which map input audio to a speaker discriminant latent space, are of paramount importance in speaker diarisation. However, there are several cha…
VoxSRC 2021: The Third VoxCeleb Speaker Recognition Challenge
Andrew Brown, Jaesung Huh, Joon Son Chung +3
The third instalment of the VoxCeleb Speaker Recognition Challenge was held in conjunction with Interspeech 2021. The aim of this challenge was to assess how well current speaker r…
With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition
Evangelos Kazakos, Jaesung Huh, Arsha Nagrani +2
In egocentric videos, actions occur in quick succession. We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order t…
VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge
Arsha Nagrani, Joon Son Chung, Jaesung Huh +6
We held the second installment of the VoxCeleb Speaker Recognition Challenge in conjunction with Interspeech 2020. The goal of this challenge was to assess how well current speaker…
Look who's not talking
Youngki Kwon, Hee Soo Heo, Jaesung Huh +2
The objective of this work is speaker diarisation of speech recordings 'in the wild'. The ability to determine speech segments is a crucial part of diarisation systems, accounting…
Playing a Part: Speaker Verification at the Movies
Andrew Brown, Jaesung Huh, Arsha Nagrani +2
The goal of this work is to investigate the performance of popular speaker recognition models on speech segments from movies, where often actors intentionally disguise their voice…
Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020
Hee Soo Heo, Bong-Jin Lee, Jaesung Huh +1
This report describes our submission to the VoxCeleb Speaker Recognition Challenge (VoxSRC) at Interspeech 2020. We perform a careful analysis of speaker recognition models based o…
Augmentation adversarial training for self-supervised speaker recognition
Jaesung Huh, Hee Soo Heo, Jingu Kang +2
The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning i…
Spot the conversation: speaker diarisation in the wild
Joon Son Chung, Jaesung Huh, Arsha Nagrani +2
The goal of this paper is speaker diarisation of videos collected 'in the wild'. We make three key contributions. First, we propose an automatic audio-visual diarisation method for…
Metric Learning for Keyword Spotting
Jaesung Huh, Minjae Lee, Heesoo Heo +2
The goal of this work is to train effective representations for keyword spotting via metric learning. Most existing works address keyword spotting as a closed-set classification pr…
In defence of metric learning for speaker recognition
Joon Son Chung, Jaesung Huh, Seongkyu Mun +7
The objective of this paper is 'open-set' speaker recognition of unseen speakers, where ideal embeddings should be able to condense information into a compact utterance-level repre…
Modeling Musical Onset Probabilities via Neural Distribution Learning
Jaesung Huh, Egil Martinsson, Adrian Kim +1
Musical onset detection can be formulated as a time-to-event (TTE) or time-since-event (TSE) prediction task by defining music as a sequence of onset events. Here we propose a nove…
The sound of my voice: speaker representation loss for target voice separation
Seongkyu Mun, Soyeon Choe, Jaesung Huh +1
Content and style representations have been widely studied in the field of style transfer. In this paper, we propose a new loss function using speaker content representation for au…
Delving into VoxCeleb: environment invariant speaker recognition
Joon Son Chung, Jaesung Huh, Seongkyu Mun
Research in speaker recognition has recently seen significant progress due to the application of neural network models and the availability of new large-scale datasets. There has b…
Phase-aware Speech Enhancement with Deep Complex U-Net
Hyeong-Seok Choi, Jang-Hyun Kim, Jaesung Huh +3
Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction.…