UDC 621.317+681.849
3 Kyiv Expert and Forensic Center of the Ministry of Internal Affairs of Ukraine, Kyiv, Ukraine
 fonoscopia@ukr.net
|
4 Odessa Scientific Research Institute of Forensic Expertise of the Ministry of Justice of Ukraine, Odessa, Ukraine
alik_shablya@gmail.com
|
5 Kyiv Scientific Research Institute of Forensic Expertise of the Ministry of Justice of Ukraine, Kyiv, Ukraine
e.tymko@kndise.gov.ua
|
|
INFORMATION REDUNDANCY IN CONSTRUCTING THE SYSTEMS FOR
AUDIO SIGNAL
EXAMINATION ON DEEP LEARNING NEURAL NETWORKS
Abstract. The methods of preliminary signal processing used to create a new toolkit for the examination of materials and means
of digital sound recording are described. It is shown that the information redundancy in creating a training base for deep learning neural
networks used for such an examination increases the efficiency of speaker identification based on the parameters of voice characteristics by about 15%.
The proposed processing methods made it possible to identify the speaker from phonograms with a duration of 1 sec.
Keywords: Morlet wavelet, time window, time-frequency transformation, speaker, identification, redundancy, neural network, spectrum, phonogram.
FULL TEXT
REFERENCES
- Solovyov V.I., Rybalskiy O.V., Zhuravel V.V., Semenova N.V. Analyzing the models of speech recognition on the basis of neural networks of deep learning for examination of digital phonograms. Cybernetics and Systems Analysis. 2021. Vol. 57, N 1. P. 133–138. https://doi.org/10.1007/s10559-021-00336-y.
- Solovyov V.I., Rybalskiy O.V., Zhuravel V.V., Zheleznyak V.K. Application of neuron networks of deep learning for exposures editing of digital phonograms. Proc. of the National Academy of Sciences of Belarus. Ser. physical and technical sciences. 2020. Vol. 65, N 4. P. 506–512. https://doi.org/10.29235/1561-8358-2020-65-4-506-512.
- Solovyov V.I., Rybalskiy O.V., Zhuravel V.V. Method of exposure of signs of the digital editing in phonograms with the use of neuron networks of the deep learning. Journal of Automation and Information Sciences. 2020. Vol. 52, Iss. 1. P. 22–28. https://doi.org//10.1615/JAutomatInfScien.v52.i1.30.
- Solovyov V.I., Rybalskiy O.V., Zhuravel V.V. Substantiating the fundamental fitness of deep learning neural networks for construction of a phonogram digital processing detection system. Cybernetics and Systems Analysis. 2020. Vol. 56, N 2. P. 326–330. https://doi.org//10.1007/s10559-020-00249-2.
- Lei Y., Scheffer N., Ferrer L., McLaren M. A novel scheme for speaker recognition using a phonetically-aware deep neural network. Proc. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (4–9 May 2014, Florence, Italy). Florence, 2014. P. 1695–1699.
- Kenny P., Gupta V., Stafylakis T., Ouellet P., Alam J. Deep neural networks for extracting Baum–Welch statistics for speaker recognition. Proc. Odyssey 2014: The Speaker and Language Recognition Workshop (16–19 June 2014, Joensuu, Finland). Joensuu, 2014. P. 293–298. URL: http://cs.uef.fi/odyssey2014/program/pdfs/28.pdf.
- Kassin S.M., Dror I.E., Kukucka J. The forensic confirmation bias: Problems, perspectives, and proposed solutions. Journal of Applied Research in Memory and Cognition. 2013. Vol. 2, Iss. 1. P. 42–52.
- Singh S. Forensic and automatic speaker recognition system. International Journal of Electrical and Computer Engineering (IJECE). 2018. Vol. 8, N 5. P. 2804–2811.
- Amali Mary Bastina A., Rama N. Biometric identification and authentication providence using fingerprint for cloud data access. International Journal of Electrical and Computer Engineering. 2017. Vol. 7, Iss. 1. P. 408–416.
- Hansen J.H.L., Hasan T. Speaker recognition by machines and humans. IEEE Signal Processing Magazine. 2015. Vol. 32, Iss. 6. P. 74–99.
- Flanagan J.L. Analysis, synthesis, and perception of speech [Russian translation]. Moscow: Svyaz', 1968. 397 p.
- Fant G. Acoustic theory of speech formation [in Russian]. Moscow: Nauka, 1964. 284 p.
- Mallat S. A wavelet tour of signal processing. New Yогk: Асаdemic Ргеss, 1999. 671 p.
- Alexandrov Yu.I. Psychophysiology [in Russian]. Moscow; St. Petersburg: Nauka, 2006. 463 p.
- Bekhtereva N.P. Psychoacoustic aspects of speech perception. Mechanisms of brain activity [in Russian]. Moscow: Nauka, 1988. 504 p.
