Zobrazeno 1 - 10
of 184
pro vyhledávání: '"Novoselov, Sergey"'
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
Investigation of Different Calibration Methods for Deep Speaker Embedding based Verification Systems
Deep speaker embedding extractors have already become new state-of-the-art systems in the speaker verification field. However, the problem of verification score calibration for such systems often remains out of focus. An irrelevant score calibration
Externí odkaz:
http://arxiv.org/abs/2203.15106
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
Autor:
Lavrentyeva, Galina, Novoselov, Sergey, Tseren, Andzhukaev, Volkova, Marina, Gorlanov, Artem, Kozlov, Alexandr
This paper describes the Speech Technology Center (STC) antispoofing systems submitted to the ASVspoof 2019 challenge. The ASVspoof2019 is the extended version of the previous challenges and includes 2 evaluation conditions: logical access use-case s
Externí odkaz:
http://arxiv.org/abs/1904.05576
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple softmax activ
Externí odkaz:
http://arxiv.org/abs/1804.10080
Deep learning is still not a very common tool in speaker verification field. We study deep convolutional neural network performance in the text-prompted speaker verification task. The prompted passphrase is segmented into word states - i.e. digits -t
Externí odkaz:
http://arxiv.org/abs/1803.05307