Audio Output Research Articles

Real-Time Object Detection Using Yolo Algorithm for Blind People

Vision is one of the foremost necessary sense that human beings use to interact with the surrounding objects. There are more than 200 visually challenges people in this world and being visually challenged obstruct lots of daily activities. Hence it is very important for blind person to know what objects they are interacting with and understand their surroundings. In this project we have created a website, which help the blind people to identify different objects in the surrounding using YOLO V3 algorithm. This integrates different technologies to build a rich website which not only helps to recognize different object in the visually challenged persons surrounding in real time but also guides them through an audio output. YOLO (You Only Look at Once) algorithm is used for object detection and recognition. This algorithm gives very close accuracy for object detection in real time and studies have also proven the this algorithm is faster and better than other object detection algorithms.

Eye(I) Still Know! – An App for the Blind Built using Web and AI

This paper proposes eye(I) still know!, a voice control solution for the visually impaired people. The main purpose is even though the blind cannot see they can still know where to go and what to do! Nearby 60% of total blind population across the world is present in India. In a time where no one likes to rely on anyone, this is a small effort to make the blind independent individuals. This can be achieved using wireless communication, voice recognition and image scanning. The application with the use of object identification will priorly inform about the barriers in the path. The software will use the camera of the device and scan all the obstacles with their corresponding distances from the user. This will be followed by audio instructions through audio output of the device. This will efficiently direct the user through his/her way.

The Effects of Biofeedback on Performance and Technique of the Boxing Jab.

A growing body of research has addressed the application of movement-based biofeedback techniques for improving sports performers’ gross motor skills. Unlike in previous research, we aimed in this study to quantify the effects of this “external” biofeedback on selected performance and technique variables for the boxing jab among both novices and experts. The technical setup included two inertial measurement units linked wirelessly to a video game system with audio output. The units were configured to provide auditory external biofeedback, based on the peak acceleration of the bag (i.e., biofeedback with an external attentional focus). Sixteen participants (8 novices and 8 experts) performed boxing jabs against the bag in blocked phases of biofeedback. When compared to baseline, the acute effects of externally focused biofeedback on peak bag acceleration were possibly positive in both retention phases for novices (d = 0.29; d = 0.41) and likely positive for experts (d = 0.41; d = 0.30), respectively. The experts’ performance improvements were accompanied by substantive increases in trunk rotation, though this was not true for the novices. Thus, technique improvements can be promoted indirectly via externally focused biofeedback, but only when these actions are within the performers’ motor repertoire. Overall, biofeedback via inertial sensors appears to be a potent technique for modifying human movement patterns in both experts and novices. This low-cost technology could be used to support training across sports, rehabilitation and human-computer interactions.

Assistant for the guest with visually impaired using Deep Learning

The lack of Braille resources in this advanced world has tied the hands of visually impaired people from soaring up. This paper takes those guests into concern and presents a solution that helps every individual especially the blinds in reading books and text from real time images. This solution converts the text obtained from text document and real world entities to aural output which lends a hand in reading text. The main idea is to build a software using a novel methodology where OCR engine receives input images and get converted into intermediate textual output that is given to Google Trans to get the audio output via earphones.

Eye(I) Still Know! – An App for the Blind Built using Web and AI

This paper proposes eye(I) still know!, a voice control solution for the visually impaired people. The main purpose is even though the blind cannot see they can still know where to go and what to do! Nearby 60% of total blind population across the world is present in India. In a time where no one likes to rely on anyone, this is a small effort to make the blind independent individuals. This can be achieved using wireless communication, voice recognition and image scanning. The application with the use of object identification will priorly inform about the barriers in the path.
 The software will use the camera of the device and scan all the obstacles with their corresponding distances from the user. This will be followed by audio instructions through audio output of the device.
 This will efficiently direct the user through his/her way.

Electronic Eye for Blind People with Object Detection and Audio Output Using Image Processing

One of the major issues faced by Blind people is detecting and recognizing an object. The objective of this project is to help the blind people because mobility of blind people is always a great problem. The mobility of blind people in unknown environment seems impossible without external help, because they don’t have any proper idea about their surroundings. So, we are developing a electronic eye which helps them to know about their surroundings and also guide them during travelling. Developing a system based on image processing using DNN algorithm which is able to labeling objects with the help of OpenCV and Tensor flow libraries and converting the labeled text in to speech and producing output in the form of audio to make the blind person aware of the object in front of him or her. The scope of this system is also measuring the distance of the object from the person and reporting the same Object detection using image processing and Machine Learning. It searches the object. We want to innovate our system the possibility of using the hearing sense to understand real time objects. For the security purpose track blind people in real time environment.

Visual DUX: A Low cost wearable device for guiding the Blind

Amongst the world's total population there exist 285 million visually impaired people. There exist several types of equipment which can lead them to a safe way but are restricted to indoor areas and are high priced. In this paper, a wearable device called VISUAL DUX is developed that helps the blind by detecting the objects in their path and directing them through the freeway either indoor or outdoor in a cost-efficient way. As object detection works better with the deep learning algorithms we have used the YOLO V3 dataset as input to the model. The YOLO method uses convolutional neural networks to detect objects by preparing bounding boxes. After getting the bounding boxes, classes of the objects are identified based on the probabilities of the bounding boxes. After finding the class of the object the direction of the obstacle is detected to direct the people with no vision with a safer path. Compared to the existing devices our device gives better accuracy and not only detecting the obstacle it also gives the safer direction to move as an audio output.

GIS Distance Learning during the COVID-19 Pandemic (Students’ Perception)

The paper deals with distance learning of geographic information systems (GIS) at the Department of Geography and Regional Development FNS CPU in Nitra using various educational materials and the JitsiMeet application during the COVID-19 pandemic. Students of bachelor study had GIS lessons in face-to-face instruction in a computer room for half of a semester. In the middle of the semester, the COVID-19 pandemic broke out in Slovakia and the face-to-face instruction had to be reoriented to the distance form of learning. The first month of distance learning took place with the help of textbooks and video tutorials, which were sent to students. The task of the students that month was to study a new subject, then students were sent a questionnaire where they had to express their opinion on learning GIS using video tutorials and textbooks, but also indicate whether they had facilities for online learning (PC, audio and video outputs, Internet) as well as to express their views and experiences with online learning as such. Although after evaluating the questionnaire, up to 71% of students answered that they had learned a new subject from the video tutorials and 57% also from GIS textbooks, several percent of students were still unfit for this form of learning. That is why we went to lessons with the free JitsyMeet app, which allows for video conferencing, screen sharing, chat, and more. The aim of the paper is to point out the perception of distance GIS learning by university students during the COVID-19 pandemic.

A Comparative Review on Object Detection System for Visually Impaired

Vision is one of the key senses allowing citizens to communicate with the natural world. There are about two hundred million blind people globally and visually disabled people obstruct numerous everyday practices. It is also really critical that blind people recognize their world and realize with which items they communicate. This paper review all the method and tool related to camera-based device to enable the blind person interpret text patterns written on items kept in hand. This is the system for helping individuals with visual disability interpret and translate text patterns to the audio output. The framework first suggests the approach to take an image from the camera and the area of the target to retrieve the object from the context and derive a text pattern from that object. Diffrent algorithm is assessed in various scenes. The observed text is linked to the blueprint and translated into the performance of the voice. Localized and binarized text patterns utilising Optical Character Recognition (OCR). The text is translated to an audio output. The voice quality is given to theblind person.

A Study on Preemptive Response to Equipment Problems in Public Address System

In this study, in preparation for equipment failure of emergency broadcasting equipment, we intend to propose a method to respond in advance to situations where abnormalities are visible.In the case of a short circuit in the speaker line in the emergency broadcasting system, high current from the power amplifier enters the line again and damages the power amplifier, making audio output impossible. As a method to prevent this, a method of separating the speaker line from other lines is mainly used in order not to affect other speaker lines when a short circuit occurs.In this study, a method for establishing a safety system with a higher level than the standard recommended by the government in emergency broadcasting system was studied and suggested. The method is to respond in advance by monitoring and analyzing the prognostic symptoms that appear before the actual failure occurs.For example, if a problem occurs in the system, the problem is solved by replacing the part or removing the time factor of the problem. However, before a failure occurs, there are cases in which the occurrence and cancellation of failure symptoms for a short period of time occur periodically or aperiodically. In this case, the possibility of actual failure is determined in advance by analyzing it as a precursor to the actual failure.In the event of a situation that appears to be a pre-specified potential failure, we propose techniques to diagnose it early and tell the manager how to take action.

CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial Networks

How can deep neural networks encode information that corresponds to words in human speech into raw acoustic data? This paper proposes two neural network architectures for modeling unsupervised lexical learning from raw acoustic inputs: ciwGAN (Categorical InfoWaveGAN) and fiwGAN (Featural InfoWaveGAN). These combine Deep Convolutional GAN architecture for audio data (WaveGAN; Donahue et al., 2019) with the information theoretic extension of GAN – InfoGAN (Chen et al., 2016) – and propose a new latent space structure that can model featural learning simultaneously with a higher level classification and allows for a very low-dimension vector representation of lexical items. In addition to the Generator and Discriminator networks, the architectures introduce a network that learns to retrieve latent codes from generated audio outputs. Lexical learning is thus modeled as emergent from an architecture that forces a deep neural network to output data such that unique information is retrievable from its acoustic outputs. The networks trained on lexical items from the TIMIT corpus learn to encode unique information corresponding to lexical items in the form of categorical variables in their latent space. By manipulating these variables, the network outputs specific lexical items. The network occasionally outputs innovative lexical items that violate training data, but are linguistically interpretable and highly informative for cognitive modeling and neural network interpretability. Innovative outputs suggest that phonetic and phonological representations learned by the network can be productively recombined and directly paralleled to productivity in human speech: a fiwGAN network trained on suit and dark outputs innovative start, even though it never saw start or even a [st] sequence in the training data. We also argue that setting latent featural codes to values well beyond training range results in almost categorical generation of prototypical lexical items and reveals underlying values of each latent code. Probing deep neural networks trained on well understood dependencies in speech bears implications for latent space interpretability and understanding how deep neural networks learn meaningful representations, as well as potential for unsupervised text-to-speech generation in the GAN framework.

Embedded Bidirectional Buck–Boost Converter in Half Bridge Class-D Audio Amplifier for Suppressing Bus Voltage Pumping

In this article, a half-bridge class-D audio amplifier (HB-CDAA) system with embedded bidirectional buck–boost converter is proposed. The proposed HB-CDAA system consists of a front-end symmetric bipolar output converter, a bidirectional buck–boost converter, and an HB-CDAA. With the help of the embedded bidirectional buck–boost converter, bus voltage pumping on the output of the front-end symmetric bipolar output converter of HB-CDAA can be suppressed. Thus, small ceramic capacitors can be used as bus capacitors to increase power density and to improve audio output quality. Furthermore, ZVS of the embedded bidirectional buck–boost converter can be achieved. The operating principle of the proposed circuit is analyzed and an experimental prototype is built. Experimental results show that ZVS of the embedded bidirectional buck–boost converter is achieved, and bus voltage pumping is successfully suppressed with small bus capacitors.

A model for spectroscopic food sample analysis using data sonification

In this paper, we propose a method to generate an audio output based on spectroscopy data in order to discriminate two classes of data, based on the features of our spectral dataset. To do this, we first perform spectral pre-processing, and then extract features, followed by machine learning, for dimensionality reduction. The features are then mapped to the parameters of a sound synthesiser, as part of the audio processing, so as to generate audio samples in order to compute statistical results and identify important descriptors for the classification of the dataset. To optimise the process, we compare Amplitude Modulation (AM) and Frequency Modulation (FM) synthesis, as applied to two real-life datasets to evaluate the performance of sonification as a method for discriminating data. FM synthesis provides a higher subjective classification accuracy as compared with to AM synthesis. We then further compare the dimensionality reduction method of Principal Component Analysis (PCA) and Linear Discriminant Analysis in order to optimise our sonification algorithm. The results of classification accuracy using FM synthesis as the sound synthesiser and PCA as the dimensionality reduction method yields a mean classification accuracies of 93.81% and 88.57% for the coffee dataset and the fruit puree dataset respectively, and indicate that this spectroscopic analysis model is able to provide relevant information on the spectral data, and most importantly, is able to discriminate accurately between the two spectra and thus provides a complementary tool to supplement current methods.

Android-based object recognition application for visually impaired

Detecting objects in real-time and converting them into an audio output was a challenging task. Recent advancement in computer vision has allowed the development of various real-time object detection applications. This paper describes a simple android app that would help the visually impaired people in understanding their surroundings. The information about the surrounding environment was captured through a phone’s camera where real-time object recognition through tensorflow’s object detection API was done. The detected objects were then converted into an audio output by using android’s text-to-speech library. Tensorflow lite made the offline processing of complex algorithms simple. The overall accuracy of the proposed system was found to be approximately 90%.

Text – To – Audio Converter

This paper aims to give an overview of Text- to- Speech converter using JAVA script. This report presents the development of a progressive web application of Text- to- Audio converter which is capable of performing different tasks. It can convert the text which is typed in the text box into audio and can also convert a pdf text to audio. Text-to-Audio Converter is a technology that converts written text from a descriptive medium to a spoken language, allowing the end user to easily understand what is written via the audio output.

Low-cost Voice Based Braille Script Communication for Teaching Aid

Though the Traditional method of teaching Braille script for the blind is simple, yet it has some potential drawbacks. Handling the marbles and the slate for a first-time does make learning very difficult. In most cases, the teacher will also be blind, so for each representation, the teacher must reach each student’s slate and change the arrangement of the marbles. This is a harder and time taking job. This project focuses on the design and development of an embedded system based electronic assistive device which eases the problem of teaching visually challenged beginner. This Project is implemented using an ordinary Braille slate with IR sensors and Raspberry Pi 2 Model B board which is cost-effective and simple. The Software is implemented in Simulink of MATLAB R2020. The placing of the marbles in the slate is sensed by the IR Proximity sensor. If the combination of the marbles placed is correct, then the Raspberry Pi’s Text to speak converter produces the audio sound output of the corresponding letter. This method provides an easy way of teaching Braille Script with less effort for the teacher.

Mobility Assistive Device for the Visually Impaired

he paper is aimed at the design of a mobility assistive device to help the visually impaired. The traditional use of a walking stick proposes its own drawbacks and limitations. Our research is motivated by the inability of the visually impaired people to ambulate and we have made an attempt to restore their independence and reduce the trouble of carrying a stick around. We offer a hands-free wearable glass which finds it utility in real-time navigation. The design of the smart glasses includes the integration of various sensors with raspberry pi. The paper presents a detailed account of the various components and the structural design of the glasses. The novelty of our work lies in providing a complete pipeline for analysis of surroundings in real-time and hence a better solution for navigating during the day to day activities using audio instructions as output.

Low-cost spectrum analyzer for trouble shooting noise sources in scanning probe microscopy

Scanning probe microscopes are notoriously sensitive to many types of external and internal interferences including electrical, mechanical, and acoustic noise. Sometimes noise can even be misinterpreted as real features in the images. Therefore, quantification of frequency and magnitude of any noise is the key to discover the source and eliminate it from the system. While commercial spectrum analyzers are perfect for this task, they are rather expensive and not always available. We present a simple, cost-effective solution in the form of an audio output from the instrument coupled to a smart phone spectrum analyzer application. Specifically, the scanning probe signal, e.g., the tunneling current of a scanning tunneling microscope, is fed to the spectrum analyzer which Fourier transforms the time domain acoustic signal into the frequency domain. When the scanning probe is in contact with the sample, but not scanning, the output is a spectrum containing both the amplitude and frequency of any periodic noise affecting the microscope itself, enabling troubleshooting to begin.

Identification and Recognition of Text and Face Using Image Processing for Visually Impaired

Nowadays, visual information is the most consequential information,so blind people or visually impaired people has this disadvantage as compulsory information about circumventing is not available to them. The objective of this project is to guide visually impaired people with an astute contrivance utilizing an Android Phone. This system predicated on Android technology is designed for them in order to solve the infeasible situation that affects the blind people. Our system presents an automated system which will provide them to read text patterns that are printed on documents. On the text patterns, localization and binarization are done utilizing OCR. The recognize text is converted to an audio and is provided to the user. Consequently, Deals with Character Recognition. The difficulty faced to identify people during conversation is a very big disadvantage for these people in many professional and edifying situations. To increase the accuracy of face recognition smartphones are utilized in these settings, we have an archetype and face recognition are tested for end users. This system uses Smartphone technology to provide audio output to the blind people.

A computational model for predicting perceived musical expression in branding scenarios

We describe the development of a computational model predicting listener-perceived expressions of music in branding contexts. Representative ground truth from multi-national online listening experiments was combined with machine learning of music branding expert knowledge, and audio signal analysis toolbox outputs. A mixture of random forest and traditional regression models is able to predict average ratings of perceived brand image on four dimensions. Resulting cross-validated prediction accuracy (R²) was Arousal: 61%, Valence: 44%, Authenticity: 55%, and Timeliness: 74%. Audio descriptors for rhythm, instrumentation, and musical style contributed most. Adaptive sub-models for different marketing target groups further increase prediction accuracy.