Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Andrei Andrusenko"'
Autor:
Aleksandr Laptev, Andrei Andrusenko, Ivan Podluzhny, Anton Mitrofanov, Ivan Medennikov, Yuri Matveev
Publikováno v:
Sensors, Vol 21, Iss 9, p 3063 (2021)
With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. For on-device speech recognition tasks, researchers and industry prefer end-to-end ASR syste
Externí odkaz:
https://doaj.org/article/1b84d4e524ff4dc399f870f076428d2a
Optimization of modern ASR architectures is among the highest priority tasks since it saves many computational resources for model training and inference. The work proposes a new Uconv-Conformer architecture based on the standard Conformer model. It
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8273c7eb005c2bc2690e3ab4eef33060
Autor:
Andrei Andrusenko, Ivan Medennikov, Aleksandr Laptev, Yuri Matveev, Anton Mitrofanov, Ivan Podluzhny
Publikováno v:
Sensors
Volume 21
Issue 9
Sensors (Basel, Switzerland)
Sensors, Vol 21, Iss 3063, p 3063 (2021)
Volume 21
Issue 9
Sensors (Basel, Switzerland)
Sensors, Vol 21, Iss 3063, p 3063 (2021)
With the rapid development of speech assistants, adapting server-intended automatic speech recognition (ASR) solutions to a direct device has become crucial. Researchers and industry prefer to use end-to-end ASR systems for on-device speech recogniti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16d9fae5e4d0c4db327f9d92b101ecba
Autor:
Yuri Y. Khokhlov, Andrei Andrusenko, Maxim Korenevsky, Ivan Medennikov, Mariya Korenevskaya, Aleksandr Laptev, Anton Mitrofanov, Aleksei Romanenko, Ivan Podluzhny, Aleksei Ilin
Neural network-based language models are commonly used in rescoring approaches to improve the quality of modern automatic speech recognition (ASR) systems. Most of the existing methods are computationally expensive since they use autoregressive langu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5cf51c8c93b6c2f3481391c44d0dce6a
http://arxiv.org/abs/2104.02526
http://arxiv.org/abs/2104.02526
Autor:
Aleksey Svischev, Roman Korostik, Andrei Andrusenko, Sergey V. Rybin, Ivan Medennikov, Aleksandr Laptev
Publikováno v:
CISP-BMEI
Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing with low-resource tasks. Using recent advances in speech synthesis (t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fb4cdf279746f5b9db30c9b363101f09
http://arxiv.org/abs/2005.07157
http://arxiv.org/abs/2005.07157
Autor:
Ivan Medennikov, Maxim Korenevsky, Tatiana Prisyach, Yuri Khokhlov, Mariya Korenevskaya, Ivan Sorokin, Tatiana Timofeeva, Anton Mitrofanov, Andrei Andrusenko, Ivan Podluzhny, Aleksandr Laptev, Aleksei Romanenko
Publikováno v:
6th International Workshop on Speech Processing in Everyday Environments (CHiME 2020).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb8a120bfddc8342d115441a79caf076
https://doi.org/10.21437/chime.2020-9
https://doi.org/10.21437/chime.2020-9
Publikováno v:
INTERSPEECH
While end-to-end ASR systems have proven competitive with the conventional hybrid approach, they are prone to accuracy degradation when it comes to noisy and low-resource conditions. In this paper, we argue that, even in such difficult cases, some en
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c2842b8ebc28f2d8b639bde7667aa1a6
http://arxiv.org/abs/2004.10799
http://arxiv.org/abs/2004.10799
Publikováno v:
Speech and Computer ISBN: 9783030602758
SPECOM
SPECOM
This paper presents an exploration of end-to-end automatic speech recognition systems (ASR) for the largest open-source Russian language data set – OpenSTT. We evaluate different existing end-to-end approaches such as joint CTC/Attention, RNN-Trans
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0140c44bc662b1a52edfe5346a7e631b
https://doi.org/10.1007/978-3-030-60276-5_4
https://doi.org/10.1007/978-3-030-60276-5_4
Autor:
Ivan Podluzhny, Ivan Sorokin, Yuri Y. Khokhlov, Andrei Andrusenko, Tatiana Prisyach, Mariya Korenevskaya, Aleksei Romanenko, Aleksandr Laptev, Maxim Korenevsky, Ivan Medennikov, Tatiana Timofeeva, Anton Mitrofanov
Publikováno v:
INTERSPEECH
Speaker diarization for real-life scenarios is an extremely challenging problem. Widely used clustering-based diarization approaches perform rather poorly in such conditions, mainly due to the limited ability to handle overlapping speech. We propose
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4ae9f336565297623daccc3ef226a606
Autor:
Ivan Sorokin, Tatiana Prisyach, Aleksei Romanenko, Oleg Petrov, Alexander Zatvornitskiy, Anton Mitrofanov, Andrei Andrusenko, Vladimir Bataev, Yuri Y. Khokhlov, Mariya Korenevskaya, Ivan Medennikov
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ebc27557daea386a85831cb6bf2556f
https://doi.org/10.21437/interspeech.2019-2645
https://doi.org/10.21437/interspeech.2019-2645