P
Pavel Korshunov
Researcher at Idiap Research Institute
Publications - 89
Citations - 2683
Pavel Korshunov is an academic researcher from Idiap Research Institute. The author has contributed to research in topics: JPEG & Privacy software. The author has an hindex of 30, co-authored 84 publications receiving 2009 citations. Previous affiliations of Pavel Korshunov include École Polytechnique Fédérale de Lausanne & École Normale Supérieure.
Papers
More filters
Proceedings ArticleDOI
UHD Video Dataset for Evaluation of Privacy
Pavel Korshunov,Touradj Ebrahimi +1 more
TL;DR: A publicly available UHD video dataset designed for evaluation of privacy issues is proposed, which demonstrates that UHD is a significantly more privacy intrusive technology when compared to HD and SD used today, and quantifies the impact of intrusivness.
Proceedings ArticleDOI
The impact of privacy protection filters on gender recognition
Natacha Ruchaud,Grigory Antipov,Pavel Korshunov,Jean-Luc Dugelay,Touradj Ebrahimi,Sid-Ahmed Berrani +5 more
TL;DR: This paper focuses on the specific task of gender recognition in images when they have been processed by privacy protection filters applied at different strengths, and compares the performance of state of the art deep learning algorithms with a subjective evaluation obtained via crowdsourcing.
Posted Content
The Speed Submission to DIHARD II: Contributions & Lessons Learned
Sahidullah,Jose Patino,Samuele Cornell,Ruiqing Yin,Sunit Sivasankaran,Hervé Bredin,Pavel Korshunov,Alessio Brutti,Romain Serizel,Emmanuel Vincent,Nicholas Evans,Sébastien Marcel,Stefano Squartini,Claude Barras +13 more
TL;DR: This paper describes the speaker diarization systems developed for the Second DIHARD Speech Diarization Challenge (DIHARD II) by the Speed team, and presents several components of the system, including categorization of domains, speech enhancement, speech activity detection, and speaker embeddings.
Proceedings ArticleDOI
When the Crowd Challenges the Lab: Lessons Learnt from Subjective Studies on Image Aesthetic Appeal
TL;DR: A long-term study on image aesthetic appeal challenged the crowdsourced assessments with typical lab methodologies in order to identify and analyze the impact of crowdsourcing environment on the reliability of subjective data.
Proceedings Article
Tampered Speaker Inconsistency Detection with Phonetically Aware Audio-visual Features
Pavel Korshunov,Michael Halstead,Diego Castan,Martin Graciarena,Mitchell McLaren,Brian Burns,Aaron Lawson,Sébastien Marcel +7 more
TL;DR: This paper demonstrates that by replacing standard MFCC features with embeddings from a DNN trained for automatic speech recognition, combined with mouth landmarks (visual features), this model can achieve a significant performance improvement on several challenging publicly available databases of speakers, for which it generated sets of tampered data.