Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Volokhov, Vladimir"'
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 verificat
Externí odkaz:
http://arxiv.org/abs/2210.16231
Autor:
Novoselov, Sergey, Lavrentyeva, Galina, Avdeeva, Anastasia, Volokhov, Vladimir, Gusev, Aleksei
Recent advances in unsupervised speech representation learning discover new approaches and provide new state-of-the-art for diverse types of speech processing tasks. This paper presents an investigation of using wav2vec 2.0 deep speech representation
Externí odkaz:
http://arxiv.org/abs/2203.15095
Autor:
Avdeeva, Anastasia, Gusev, Aleksei, Korsunov, Igor, Kozlov, Alexander, Lavrentyeva, Galina, Novoselov, Sergey, Pekhovsky, Timur, Shulipa, Andrey, Vinogradova, Alisa, Volokhov, Vladimir, Smirnov, Evgeny, Galyuk, Vasily
This paper presents a description of STC Ltd. systems submitted to the NIST 2021 Speaker Recognition Evaluation for both fixed and open training conditions. These systems consists of a number of diverse subsystems based on using deep neural networks
Externí odkaz:
http://arxiv.org/abs/2111.02298
Autor:
Gusev, Aleksei, Volokhov, Vladimir, Andzhukaev, Tseren, Novoselov, Sergey, Lavrentyeva, Galina, Volkova, Marina, Gazizullina, Alice, Shulipa, Andrey, Gorlanov, Artem, Avdeeva, Anastasia, Ivanov, Artem, Kozlov, Alexander, Pekhovsky, Timur, Matveev, Yuri
Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets. From the practical point of vi
Externí odkaz:
http://arxiv.org/abs/2002.06033
Autor:
Novoselov, Sergey, Gusev, Aleksei, Ivanov, Artem, Pekhovsky, Timur, Shulipa, Andrey, Lavrentyeva, Galina, Volokhov, Vladimir, Kozlov, Alexandr
This paper presents the Speech Technology Center (STC) speaker recognition (SR) systems submitted to the VOiCES From a Distance challenge 2019. The challenge's SR task is focused on the problem of speaker recognition in single channel distant/far-fie
Externí odkaz:
http://arxiv.org/abs/1904.06093
Publikováno v:
Computer Vision in Control Systems-2; 2015, p251-276, 26p
Publikováno v:
2015 17th Conference of Open Innovations Association (FRUCT); 2015, p136-141, 6p
Publikováno v:
Proceedings of 15th Conference of Open Innovations Association FRUCT; 2014, p112-118, 7p
Publikováno v:
Proceedings of 15th Conference of Open Innovations Association FRUCT; 2014, p144-149, 6p
Publikováno v:
Proceedings of the International MultiConference of Engineers & Computer Scientists 2013; 2013, p1-6, 6p