Natural Speech Signal Recognition Algorithm

Speech recognition technologies are becoming more and more part of our lives, providing a convenient way to control a variety of electronic devices - voice control. One of the current problems that is solved in the development of such control systems is the problem of insufficient accuracy of voice command recognition. Improvements are being made to increase reliability, independence from individual voice characteristics, and reduce the negative impact of background noise on recognition quality. The paper presents an algorithm for recognizing and processing user intentions using a neural network built on the principle of understanding natural language and processing audio signals for use in the user support system.

Download Full-text

Design Of A Voice Controlled Home Automation System Using Deep Learning Convolutional Neural Network (DL-CNN)

Telekontran : Jurnal Ilmiah Telekomunikasi, Kendali dan Elektronika Terapan ◽

10.34010/telekontran.v8i1.3078 ◽

2020 ◽

Vol 8 (1) ◽

pp. 57-73

Author(s):

Lery Sakti Ramba

Keyword(s):

Deep Learning ◽

Speech Recognition ◽

Background Noise ◽

Electronic Devices ◽

Recognition System ◽

Background Intensity ◽

Automation System ◽

Home Automation ◽

Speech Recognition System ◽

Home Automation System

The purpose of this research is to design home automation system that can be controlled using voice commands. This research was conducted by studying other research related to the topics in this research, discussing with competent parties, designing systems, testing systems, and conducting analyzes based on tests that have been done. In this research voice recognition system was designed using Deep Learning Convolutional Neural Networks (DL-CNN). The CNN model that has been designed will then be trained to recognize several kinds of voice commands. The result of this research is a speech recognition system that can be used to control several electronic devices connected to the system. The speech recognition system in this research has a 100% success rate in room conditions with background intensity of 24dB (silent), 67.67% in room conditions with 42dB background noise intensity, and only 51.67% in room conditions with background intensity noise 52dB (noisy). The percentage of the success of the speech recognition system in this research is strongly influenced by the intensity of background noise in a room. Therefore, to obtain optimal results, the speech recognition system in this research is more suitable for use in rooms with low intensity background noise.

Download Full-text

The algorithm of the color signal recognition at landing an unmanned aerial vehicle on an aircraft carrier in autonomous mode

Automation. Modern Techologies ◽

10.36652/0869-4931-2020-74-2-78-84 ◽

2020 ◽

pp. 78

Keyword(s):

Unmanned Aerial Vehicle ◽

Treatment Method ◽

Recognition Algorithm ◽

Connected Components ◽

Preliminary Treatment ◽

Signal Recognition ◽

Aircraft Carrier ◽

Halftone Image ◽

Glide Path ◽

Aerial Vehicle

The movement along the glide path of an unmanned aerial vehicle during landing on an aircraft carrier is investigated. The implementation of this task is realized in the conditions of radio silence of the aircraft carrier. The algorithm for treatment information from an optical landing system installed on an aircraft carrier is developed. The algorithm of the color signal recognition assumes the usage of the image frame preliminary treatment method via a downsample function, that performs the decimation process, the HSV model, the Otsu’s method for calculating the binarization threshold for a halftone image, and the method of separating the connected Two-Pass components. Keywords unmanned aerial vehicle; aircraft carrier; approach; glide path; optical landing system; color signal recognition algorithm; decimation; connected components; halftone image binarization

Download Full-text

The Effects of Preschoolers’ Media Usage Habits on Their Daily Life and Sustainability

Discourse and Communication for Sustainable Education ◽

10.2478/dcse-2019-0022 ◽

2019 ◽

Vol 10 (2) ◽

pp. 112-128

Author(s):

Begum Canaslan Akyar ◽

Özkan Sapsaglam

Keyword(s):

Home Environment ◽

Negative Impact ◽

Electronic Devices ◽

Media Usage ◽

Case Study Design ◽

Digital World ◽

Digital Contents ◽

Reported Study ◽

Different Levels

Abstract Today’s children are born into a digital world and are exposed to various electronic devices and digital contents both in the home environment and other environments since the first years of life. Children, who are a natural recipient of the environment in which they live, are exposed to the effects of the digital world at different levels and reflect these effects in different ways. The purpose of the reported study is to investigate if preschoolers’ daily media usage habits affects their drawings. This study is planned according to the case study design of qualitative research methods. The study was conducted with 15 preschoolers and their parents. There were nine boys and six girls in the study. The preschoolers’ drawings and their parents’ interview data were analyzed by using the descriptive analyzing method. The study result shows that there are differences between boys and girls media usage habits. Boys spend more time with media tools than girls. Additionally, boys are exposed to more inappropriate content because of their preferences. The analysis of their drawings revealed that boys are more affected than girls from media contents since boys’ drawings include more characters from media than girls. It can thus be suggested that media tools might be harmful when they are used in a developmentally inappropriate way, and excessive media tool usage has negative impact on children. Therefore, the reported study recommends that parents and caregivers take some precautions to limit preschoolers from spending time with media tools and to control content of children’s activity.

Download Full-text

Regional Signal Recognition of Body Sounds

Journal of Intelligent Systems with Applications ◽

10.54856/jiswa.202112187 ◽

2021 ◽

pp. 157-160

Author(s):

Osman Balli ◽

Yakup Kutlu

Keyword(s):

Neural Network ◽

Control System ◽

Neural Network Model ◽

External Environment ◽

The Body ◽

Educational Success ◽

Digital Analysis ◽

Signal Recognition ◽

Audio Signals ◽

Different Parts

One of the most important signals in the field of biomedicine is audio signals. Sound signals obtained from the body give us information about the general condition of the body. However, the detection of different sounds when recording audio signals belonging to the body or listening to them by doctors makes it difficult to diagnose the disease from these signals. In addition to isolating these sounds from the external environment, it is also necessary to separate their sounds from different parts of the body during the analysis. Separation of heart, lung and abdominal sounds will facilitate digital analysis, in particular. In this study, a dataset was created from the lungs, heart and abdominal sounds. MFCC (Mel Frekans Cepstrum Coefficient) coefficient data were obtained. The obtained coefficients were trained in the CNN (Convolution Neural Network) model. The purpose of this study is to classify audio signals. With this classification, a control system can be created. In this way, erroneous recordings that may occur when recording physicians' body voices will be prevented. When looking at the results, the educational success is about 98% and the test success is about 85%.

Download Full-text

THE EFFECT OF DIFFERENT OCCUPATIONAL BACKGROUND NOISES ON VOICE RECOGNITION ACCURACY

Journal of Computing and Information Science in Engineering ◽

10.1115/1.4053521 ◽

2022 ◽

pp. 1-30

Author(s):

Song Li ◽

Mustafa Ozkan Yerebakan ◽

Yue Luo ◽

Ben Amaba ◽

William Swope ◽

...

Keyword(s):

Background Noise ◽

Recognition Accuracy ◽

Voice Recognition ◽

Recognition Algorithm ◽

Control Mechanisms ◽

Recognition Algorithms ◽

Significant Performance ◽

Industrial Productivity ◽

Overall Performance ◽

Occupational Background

Abstract Voice recognition has become an integral part of our lives, commonly used in call centers and as part of virtual assistants. However, voice recognition is increasingly applied to more industrial uses. Each of these use cases has unique characteristics that may impact the effectiveness of voice recognition, which could impact industrial productivity, performance, or even safety. One of the most prominent among them is the unique background noises that are dominant in each industry. The existence of different machinery and different work layouts are primary contributors to this. Another important characteristic is the type of communication that is present in these settings. Daily communication often involves longer sentences uttered under relatively silent conditions, whereas communication in industrial settings is often short and conducted in loud conditions. In this study, we demonstrated the importance of taking these two elements into account by comparing the performances of two voice recognition algorithms under several background noise conditions: a regular Convolutional Neural Network (CNN) based voice recognition algorithm to an Auto Speech Recognition (ASR) based model with a denoising module. Our results indicate that there is a significant performance drop between the typical background noise use (white noise) and the rest of the background noises. Also, our custom ASR model with the denoising module outperformed the CNN based model with an overall performance increase between 14-35% across all background noises. . Both results give proof that specialized voice recognition algorithms need to be developed for these environments to reliably deploy them as control mechanisms.

Download Full-text

Auditory Attention

Oxford Research Encyclopedia of Psychology ◽

10.1093/acrefore/9780190236557.013.778 ◽

2021 ◽

Author(s):

C. Philip Beaman

Keyword(s):

Background Noise ◽

Traffic Noise ◽

Electronic Devices ◽

Auditory Attention ◽

The Other ◽

Background Music ◽

Modern World ◽

Auditory Distraction ◽

Environmental Sounds ◽

The One

The modern world is noisy. Streets are cacophonies of traffic noise; homes and workplaces are replete with bleeping timers, announcements, and alarms. Everywhere there is the sound of human speech—from the casual chatter of strangers and the unwanted intrusion from electronic devices through to the conversations with friends and loved ones one may actually wish to hear. Unlike vision, it is not possible simply to “close our ears” and shut out the auditory world and nor, in many cases, is it desirable. On the one hand, soft background music or environmental sounds, such as birdsong or the noise of waves against the beach, is often comfortingly pleasurable or reassuring. On the other, alarms are usually auditory for a reason. Nevertheless, people somehow have to identify, from among the babble that surrounds them, the sounds and speech of interest and importance and to follow the thread of a chosen speaker in a crowded auditory environment. Additionally, irrelevant or unwanted chatter or other background noise should not hinder concentration on matters of greater interest or importance—students should ideally be able to study effectively despite noisy classrooms or university halls while still being open to the possibility of important interruptions from elsewhere. The scientific study of auditory attention has been driven by such practical problems: how people somehow manage to select the most interesting or most relevant speaker from the competing auditory demands made by the speech of others or isolate the music of the band from the chatter of the nightclub. In parallel, the causes of auditory distraction—and how to try to avoid it where necessary—have also been subject to scrutiny. A complete theory of auditory attention must account for the mechanisms by which selective attention is achieved, the causes of auditory distraction, and the reasons why individuals might differ in their ability in both cases.

Download Full-text