scholarly journals Discriminant Analysis of Voice Commands in the Presence of an Unmanned Aerial Vehicle

Information ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 23
Author(s):  
Marzena Mięsikowska
Keyword(s):  
Discriminant Analysis ◽  
Unmanned Aerial Vehicle ◽  
Speech Intelligibility ◽  
Measuring Equipment ◽  
Verbal Communication ◽  
Mel Frequency Cepstral Coefficients ◽  
Sound Levels ◽  
Aerial Vehicle ◽  
Cepstral Coefficients

The aim of this study was to perform discriminant analysis of voice commands in the presence of an unmanned aerial vehicle equipped with four rotating propellers, as well as to obtain background sound levels and speech intelligibility. The measurements were taken in laboratory conditions in the absence of the unmanned aerial vehicle and the presence of the unmanned aerial vehicle. Discriminant analysis of speech commands (left, right, up, down, forward, backward, start, and stop) was performed based on mel-frequency cepstral coefficients. Ten male speakers took part in this experiment. The unmanned aerial vehicle hovered at a height of 1.8 m during the recordings at a distance of 2 m from the speaker and 0.3 m above the measuring equipment. Discriminant analysis based on mel-frequency cepstral coefficients showed promising classification of speech commands equal to 76.2% for male speakers. Evaluated speech intelligibility during recordings and obtained sound levels in the presence of the unmanned aerial vehicle during recordings did not exclude verbal communication with the unmanned aerial vehicle for male speakers.

scholarly journals СИСТЕМА РАСПОЗНАВАНИЯ СТЕГАНОГРАФИЧЕСКИ-ПРЕОБРАЗОВАННЫХ ГОЛОСОВЫХ КОМАНД УПРАВЛЕНИЯ БПЛА

2018 ◽  
pp. 20-28
Author(s):  
Александр Юрьевич Лавриненко ◽  
Юрий Анатольевич Кочергин ◽  
Георгий Филимонович Конахович
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Vehicle Control ◽  
Mel Frequency Cepstral Coefficients ◽  
Control Information ◽  
Cepstral Analysis ◽  
Voice Control ◽  
Aerial Vehicle ◽  
Cepstral Coefficients ◽  
The Difference ◽  
The Mathematical Model

It is created the system of recognition the steganographic-transformed voice commands of unmanned aerial vehicle control based on a cepstral analysis. It provides effective recognition and hidden commands transmission of to the board of an unmanned aerial vehicle, by converting voice control commands into a kind of steganographic characteristics vector, which implies the concealment of voice control information of an unmanned aerial vehicle. The mathematical model of the algorithm for calculating the mel-frequency cepstral coefficients and the recognition classifier of voice control commands for the solution of the problem of semantic identification and securing the control information of the unmanned aerial vehicle in the communication channel is synthesized. A software package has been developed that includes tools for compiling the base of reference voice images of subjects of management for training and testing the system for recognizing steganographic-transformed voice commands of the unmanned aerial vehicle control based on the cepstral analysis and computer models of the proposed methods and algorithms for recognition voice control commands in the MATLAB environment. The expediency of applying the proposed system for recognizing steganographic-transformed voice commands of the unmanned aerial vehicle control based on a cepstral analysis is substantiated and experimentally proved. An algorithm is presented for calculating the mel-frequency cepstral coefficients that appear in the role of the main features of recognition and the result of the steganographic transformation of speech, where for the evaluation of automatic recognition of voice commands using the results of classifier constructed by the criterion of minimum distance in the role which acts as the variance of the difference of the expectation of a mel-frequency cepstral coefficients. The obtained results of the experimental research allow to draw a conclusion about the expediency of further practical application of the developed system of recognition the steganographic-transformed voice commands of the unmanned aerial vehicle control based on the cepstral analysis

scholarly journals MATHEMATICAL MODELLING OF THE UNMANNED AERIAL VEHICLE DYNAMICS

2018 ◽  
pp. 37-44
Author(s):  
V. Y. Stepanov
Keyword(s):  
Mathematical Model ◽  
Mathematical Modelling ◽  
Unmanned Aerial Vehicle ◽  
Vehicle Dynamics ◽  
Point Of View ◽  
Dynamics Analysis ◽  
Aerial Vehicle ◽  
Main Components ◽  
Controlled Object

The article gives a classification of the main components of unmanned aerial vehicle (UAV) systems, gives the areas in which the application of UAVs is actual in practice today. Further, the UAV is considered in more detail from the point of view of its flight dynamics analysis, the equation necessary for creating a mathematical model, as well as the model of an ordinary dynamic system as a non-stationary nonlinear controlled object, is given. Next, a description of the developed software for modeling and a description of program algorithm are given. Finally, a conclusion describes the necessary directions for further scientific researches.

Classification of Terrain Types in Unmanned Aerial Vehicle Images

2018 ◽  
Author(s):  
Inon Wiratsin ◽  
Veerapong Suchaiporn ◽  
Pojchara Trainorapong ◽  
Jirachaipat Chaichinvara ◽  
Sakwaroon Rattanajitdamrong ◽  
...  
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Aerial Vehicle

scholarly journals Pilot Measurement of Illuminance in the Context of Light Pollution Performed with an Unmanned Aerial Vehicle

2020 ◽  
Vol 12 (13) ◽  
pp. 2124
Author(s):  
Przemyslaw Tabaka
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Measuring Equipment ◽  
Large City ◽  
Measurement Data ◽  
Luminous Flux ◽  
Light Pollution ◽  
Open Area ◽  
Pollution Effect ◽  
Aerial Vehicle

This article presents the methodology and results of pilot field illuminance measurements using an unmanned aerial vehicle (UAV). The main goal of the study was to quantify the luminous flux emitted in the upper hemisphere (toward the sky) based on obtained measurement data. The luminous flux emitted toward the sky is the source of undesirable light pollution. For test purposes, a height-adjustable mobile park lantern was constructed, at the top of which any type of luminaire can be installed. In the pilot measurements, two real opal sphere-type luminaires were considered. The lantern was situated in an open area located away from a large city agglomeration. To determine the unusable luminous flux, illuminance was measured, placing the necessary measuring equipment on board a UAV. The measurements were supplemented with the registration of illuminance on the ground upon which the lantern was installed. Based on these data, the useful luminous flux was calculated. The findings show that UAVs may be successfully used for the assessment of the influence of lighting on the light pollution effect.

scholarly journals Voice Disorder Classification Based on Multitaper Mel Frequency Cepstral Coefficients Features

2015 ◽  
Vol 2015 ◽  
pp. 1-12 ◽  
Author(s):  
Ömer Eskidere ◽  
Ahmet Gürhanlı
Keyword(s):  
Voice Disorder ◽  
Mel Frequency Cepstral Coefficients ◽  
Essential Information ◽  
Audio Processing ◽  
Voice Signal ◽  
Window Technique ◽  
Normal Voice ◽  
Cepstral Coefficients ◽  
Better Than

The Mel Frequency Cepstral Coefficients (MFCCs) are widely used in order to extract essential information from a voice signal and became a popular feature extractor used in audio processing. However, MFCC features are usually calculated from a single window (taper) characterized by large variance. This study shows investigations on reducing variance for the classification of two different voice qualities (normal voice and disordered voice) using multitaper MFCC features. We also compare their performance by newly proposed windowing techniques and conventional single-taper technique. The results demonstrate that adapted weighted Thomson multitaper method could distinguish between normal voice and disordered voice better than the results done by the conventional single-taper (Hamming window) technique and two newly proposed windowing methods. The multitaper MFCC features may be helpful in identifying voices at risk for a real pathology that has to be proven later.

Sign in / Sign up

Export Citation Format

Share Document