AIConfPaper
← Search

Vladimir Volokhov

3 accepted papers

2025

ITMO language diarization and identification systems for the DISPLACE 2024 challenge

Egor Ausev, Vladimir Volokhov, Sergey Novoselov, Vladislav Marchevskiy, Ekaterina Shangina, Alexey Logunov
ICASSP 2025accepted

This paper describes our language diarization and identification systems developed for far-field recorded group conversations. Our approach has a two-stage design and relies on classical methods, such as spectral clustering of language embeddings. The heuristic bypass (HBP) method was utilized to ge…

Cited by 0Source ↗Scholar ↗
2025

In Search of Optimal Pretraining Strategy for Robust Speaker Recognition

Nikita Khmelev, Stepan Malykh, Alexander Anikin, Anastasia Korenevskaya, Sergey Novoselov, Vladimir Volokhov +3
ICASSP 2025accepted

While demonstrating state-of-the-art results in the microphone channel domain (VoxCeleb protocols), contemporary speaker verification systems are not often tested in challenging acoustic environments such as telephone channel or far-field microphone. This paper compares modern pretraining strategies…

Cited by 0Source ↗Scholar ↗
2023

Universal Speaker Recognition Encoders for Different Speech Segments Duration

Sergey Novoselov, Vladimir Volokhov, Galina Lavrentyeva
ICASSP 2023accepted

Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker verification and systems trained on long segments are super…

Cited by 0Source ↗Scholar ↗