Zobrazeno 1 - 10
of 16
pro vyhledávání: '"E. S. Azarov"'
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 21, Iss 4, Pp 110-117 (2023)
The task of detecting vocal abnormalities is characterized by a small amount of available data for training, as a consequence of which classification systems that use low-dimensional data are the most relevant. We propose to use LASSO (least absolute
Externí odkaz:
https://doaj.org/article/adc86e638e1b4ae4b317c0a2c504a89c
Publikováno v:
Informatika, Vol 20, Iss 1, Pp 102-112 (2023)
Objectives. The problem of developing a method for calculating small-sized spectral features that increases the efficiency of existing machine learning systems for analyzing and classifying voice signals is being solved.Methods. Spectral features are
Externí odkaz:
https://doaj.org/article/32f74c4cc45949708e37a2ae2f21b0fb
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 20, Iss 1, Pp 73-82 (2022)
The paper describes an approach to design a system for analyzing and classification of a voice signal based on perturbation parameters and cepstral representation. Two variants of the cepstral representation of the voice signal are considered: based
Externí odkaz:
https://doaj.org/article/fc2c5f52f8be4cf782994ceebcc05737
Autor:
R. S. Vashkevich, E. S. Azarov
Publikováno v:
Informatika, Vol 17, Iss 2, Pp 36-43 (2020)
The paper investigates the problem of voice activity detection from a noisy sound signal. An extremely compact convolutional neural network is proposed. The model has only 385 trainable parameters. Proposed model doesn’t require a lot of computatio
Externí odkaz:
https://doaj.org/article/892d054342b7416282cf66bd60992042
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 18, Iss 2, Pp 23-29 (2020)
The paper presents a speech generative model that provides an efficient way of generating speech waveform from its amplitude spectral envelopes. The model is based on hybrid speech representation that includes deterministic (harmonic) and stochastic
Externí odkaz:
https://doaj.org/article/4adc279fa7e84b8c958f4681c74eb7a0
Publikováno v:
Informatika, Vol 16, Iss 2, Pp 119-124 (2019)
Two periods of scientific activity of Professor Alexander Alexandrovich Petrovsky, who was a member of the editorial board of the journal "Informatics" for 15 years (2004–2019), are presented. The main scientific results, his contribution to the de
Externí odkaz:
https://doaj.org/article/b8f22f1edc2e43c7b201950a9475615e
Publikováno v:
Doklady Belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki, Vol 0, Iss 7, Pp 313-317 (2019)
The paper presents a combined noise and acoustic feedback reduction algorithm. The algorithm is based on spectral subtraction and is robust to rapid changes in acoustic feedback path which makes it suitable for using in a smartphone-based hearing aid
Externí odkaz:
https://doaj.org/article/00914ec5f78f4a908e45aab1a34d26d7
Publikováno v:
Informatika, Vol 0, Iss 2, Pp 5-24 (2016)
An implementation of digital hearing aid based on the mobile computing platform iPhone is proposed. The developed signal processing scheme has a low delay, takes into account characteristics of the computing platform and allows to perform the correct
Externí odkaz:
https://doaj.org/article/5657d507dc18471b8c6df88db17e9cf5
Publikováno v:
Nanobiotechnology Reports. 16:663-667
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::61ec69f8276ec5682d521108f441fea4
https://doi.org/10.1134/s2635167621050207
https://doi.org/10.1134/s2635167621050207
Publikováno v:
Arid Ecosystems. 6:100-106
Variations of 87Sr/86Sr ratios in different natural objects make it possible to obtain new data having great importance for the identification of the possible place of origin and migration routes of ancient humans. The discussed data were obtained fr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50c041fa4d332ba678e4cf218ec7c842
https://doi.org/10.1134/s2079096116020116
https://doi.org/10.1134/s2079096116020116