A
Aleksei Gusev
Publications - 11
Citations - 104
Aleksei Gusev is an academic researcher. The author has contributed to research in topics: Speaker recognition & Speaker diarisation. The author has an hindex of 4, co-authored 9 publications receiving 57 citations.
Papers
More filters
Proceedings ArticleDOI
Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances.
Aleksei Gusev,Vladimir Volokhov,Tseren Andzhukaev,Sergey Novoselov,Galina Lavrentyeva,Marina Volkova,Alice Gazizullina,Andrey Shulipa,Artem Gorlanov,Anastasia Avdeeva,Artem Ivanov,Alexander Kozlov,Timur Pekhovsky,Yuri Matveev +13 more
TL;DR: In this paper, the authors proposed approaches aimed to improve the quality of far-field speaker verification systems in the presence of environmental noise, reverberation and reduce the system quality degradation for short utterances.
Proceedings ArticleDOI
STC Speaker Recognition Systems for the VOiCES from a Distance Challenge.
Sergey Novoselov,Aleksei Gusev,Artem Ivanov,Timur Pekhovsky,Andrey Shulipa,Galina Lavrentyeva,Vladimir Volokhov,Alexandr Kozlov +7 more
TL;DR: In this article, the authors investigated different deep neural networks architectures for speaker embedding extraction to solve the task and showed that deep networks with residual frame level connections outperform more shallow architectures.
Proceedings ArticleDOI
Speaker Diarization with Deep Speaker Embeddings for DIHARD Challenge II.
Sergey Novoselov,Aleksei Gusev,Artem Ivanov,Timur Pekhovsky,Andrey Shulipa,Anastasia Avdeeva,Artem Gorlanov,Alexandr Kozlov +7 more
Posted Content
Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances
Aleksei Gusev,Vladimir Volokhov,Tseren Andzhukaev,Sergey Novoselov,Galina Lavrentyeva,Marina Volkova,Alice Gazizullina,Andrey Shulipa,Artem Gorlanov,Anastasia Avdeeva,Artem Ivanov,Alexander Kozlov,Timur Pekhovsky,Yuri Matveev +13 more
TL;DR: This paper presents approaches aimed to improve the quality of far-field speaker verification systems in the presence of environmental noise, reverberation and reduce the system qualitydegradation for short utterances and confirms that ResNet architectures outperform the standard x-vector approach in terms of speaker verification quality.
Proceedings ArticleDOI
STC-Innovation Speaker Recognition Systems for Far-Field Speaker Verification Challenge 2020.
Aleksei Gusev,Vladimir Volokhov,Alisa Vinogradova,Tseren Andzhukaev,Andrey Shulipa,Sergey Novoselov,Timur Pekhovsky,Alexander Kozlov +7 more
TL;DR: A number of experiments on x vector-based and ResNet-like architectures show that ResNetbased networks outperform x-vector-based systems.