7 August 2017 Research of neural network classifier in speaker recognition module for automated system of critical use
Author Affiliations +
Proceedings Volume 10445, Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2017; 1044521 (2017) https://doi.org/10.1117/12.2280930
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2017, 2017, Wilga, Poland
Abstract
The article studies the dependence of the quality of speakers recognition by convolutional neural network from the type of chosen informative features for use it in automated systems for critical use especially when they are used in the environmental influences. The environmental influences are the noise of high level with a spectrum that correlates with the spectrum of the speech signal or the signal of speaker simulator. Сonvolutional network operation principles for the case of speaker signal recognition, as well as experiments on neural network training and the recognition of speakers on a test samples have been considered. According to the research, it was concluded that the bark-cepstral coefficients make it possible to perform recognition with greater reliability than the spectral parameters of the signal.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mykola M. Bykov, Viacheslav V. Kovtun, Andrzej Smolarz, Mukhtar Junisbekov, Aliya Targeusizova, Maksabek Satymbekov, "Research of neural network classifier in speaker recognition module for automated system of critical use", Proc. SPIE 10445, Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2017, 1044521 (7 August 2017); doi: 10.1117/12.2280930; https://doi.org/10.1117/12.2280930
PROCEEDINGS
7 PAGES


SHARE
Back to Top