Information Redundancy in Constructing Systems for Audio Signal Examination on Deep Learning Neural Networks

被引：0

作者：

V. I. Solovyov

O. V. Rybalskiy

V. V. Zhuravel

A. N. Shablya

E. V. Tymko

机构：

[1] Silentium Systems,

[2] National Academy of Internal Affairs,undefined

[3] Kyiv Expert and Forensic Center of the Ministry of Internal Affairs of Ukraine,undefined

[4] Odessa Scientific Research Institute of Forensic Expertise of the Ministry of Justice of Ukraine,undefined

[5] Kyiv Scientific Research Institute of Forensic Expertise of the Ministry of Justice of Ukraine,undefined

来源：

Cybernetics and Systems Analysis | 2022年 / 58卷

关键词：

Morlet wavelet; time window; time-frequency transformation; speaker; identification; redundancy; neural network; spectrum; phonogram;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Preliminary signal processing methods used to create new tools to examine materials and digital sound recording means are described. It is shown that using information redundancy when creating a training base for deep learning neural networks used for such examination increases speaker identification efficiency based on voice characteristic parameters by about 15%. It is shown that the proposed processing methods enable speaker identification based on phonograms that are 1 second long.

引用

页码：8 / 15

页数：7

共 50 条

[21] Multichannel Audio Source Separation With Deep Neural Networks
Nugraha, Aditya Arie
Liutkus, Antoine
Vincent, Emmanuel
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2016, 24 (09) : 1652 - 1664
[22] AUDIO CONCEPT CLASSIFICATION WITH HIERARCHICAL DEEP NEURAL NETWORKS
Ravanelli, Mirco
Elizalde, Benjamin
Ni, Karl
Friedland, Gerald
2014 PROCEEDINGS OF THE 22ND EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2014, : 606 - 610
[23] Constructing exact representations of quantum many-body systems with deep neural networks
Giuseppe Carleo
Yusuke Nomura
Masatoshi Imada
Nature Communications, 9
[24] Audio Event Classification Using Deep Neural Networks
Kons, Zvi
Toledo-Ronen, Orith
14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 1481 - 1485
[25] Designing Audio Equalization Filters by Deep Neural Networks
Pepe, Giovanni
Gabrielli, Leonardo
Squartini, Stefano
Cattani, Luca
APPLIED SCIENCES-BASEL, 2020, 10 (07):
[26] Audio Scene Classification with Deep Recurrent Neural Networks
Huy Phan
Koch, Philipp
Katzberg, Fabrice
Maass, Marco
Mazur, Radoslaw
Mertins, Alfred
18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 3043 - 3047
[27] Combined Neural Networks Based on Deep Learning for Signal Detection in Aeronautical Communications
Hou J.
Lü Z.
Xu M.
Wu P.
Liu Y.
Zhang X.
Chen Z.
Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University, 2019, 54 (04): : 863 - 869and878
[28] Constructing artificial boundary condition of dispersive wave systems by deep learning neural network
Zheng, Zijun
Shao, Jiaru
Zhang, Ziying
PHYSICA SCRIPTA, 2023, 98 (12)
[29] Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation
Xu, Qi
Li, Yaxin
Shen, Jiangrong
Liu, Jian K.
Tang, Huajin
Pan, Gang
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 7886 - 7895
[30] Frequency Regularization: Reducing Information Redundancy in Convolutional Neural Networks
Zhao, Chenqiu
Dong, Guanfang
Zhang, Shupei
Tan, Zijie
Basu, Anup
IEEE ACCESS, 2023, 11 : 106793 - 106802

← 1 2 3 4 5 →