Персона: Леонова, Наталия Михайловна
Email Address
Birth Date
Результаты поиска
Intelligent Processing of Speech Information in the Tasks of Noise Reduction for Communication Tools at the Objects of the Digital Economy
© 2020 IEEE.The relevance of the development of methodological and technical means of noise cleaning of acoustic signals is substantiated. The analysis of noise reduction software used in practice is given, their main disadvantages are revealed. The paper considers an approach based on intelligent digital processing of a noisy acoustic signal with unknown parameters of noise and interference. The approach implements a technique for recognizing noise and interference parameters when processing two-dimensional images obtained by transforming a noisy acoustic signal into dynamic sonograms. This allows you to recognize and classify various types of interference, as well as their parameters based on the use of special tools for processing graphic information. The technology of automatic analysis of noisy acoustic information in the framework of the proposed approach is considered.
Algorithm Allows Changing the Required Voice to a Predetermined One Using a Surrogate Voice
© 2022 IEEE.This article describes the algorithm for changing the input voice to a predefined voice. The main principle and new principle of the algorithm is the creation of a surrogate voice, the use of which will significantly reduce the time spent on the operation of the algorithm. The work consists of 3 main stages: training the neural network model according to the given parameters of the initial voice; calculation of filters that affect the characteristics of speech: tempo, speed, intonation, defects, as well as musical characteristics; applying the received filters to the input - variable voice.
Model of Passive Endure Echolocation
© 2022 IEEE.In the course of work, a study was carried out to identify patterns in the signal changes of low-frequency antennas and to identify the dependence on the type and material of obstacles, in particular buildings and domestic premises. the main task was to find the signal source in the premises of different layouts. The developed system is designed to determine the key points for the triangulation of Wi-Fi signal sources in urban areas. The main functions are searching for quality zones with the lowest errors on the resulting data, defining the values obtained in the course of the algorithm for easy comparison with the real installation. Visualization of a given room plan with marked key points.
Antenna for Passive Echolocation
© 2022 IEEE.The article describes the process of simulation of the narrow-directional antenna in MMANA-GAL program. Based on the construction of the theoretical, experimental models the main factors influencing the width of the petals are revealed. Calculated calculation formulas, allowing the calculation of the resistance and the size of obstacles that adjust the acceptance and transmission of the antenna signal. The diagrams of the orientation for different frequencies. Tapering the main lobe of the antenna allows signals to be read at a specific predetermined angle, reducing error and the number of spurious signals.