Voice-based System Research Articles

Empowering the Visually Impaired: A Voice-Based Email Management System

The research focuses on developing a voice-based email system to assist visually impaired users in sending and receiving emails independently. Existing systems, like screen readers, pose challenges when it comes to attaching files or navigating complex email interfaces. To address these issues, the proposed solution leverages Speech-to-Text (STT) and Text- toSpeech (TTS) technologies, along with Microsoft Speech Recognition, to allow users to manage emails and attachments through voice commands. This system simplifies tasks such as file searches, email composition, and sending attachments, reducing the need for keyboard navigation. Implemented using Python libraries like GTTS and speech recognition, it enables visually impaired users to interact with email systems autonomously. The approach focuses on improving accessibility, reducing cognitive load, and providing a userfriendly interface. Future extensions could include additional services like messaging and voicecontrolled applications, further enhancing usability for both visually impaired and illiterate users.

VoiceBack: Design of Artificial Intelligence-Driven Voice-Based Feedback System for Customer-Agency Communication in Online Travel Services

Online travel booking has become increasingly popular; however, most travel websites do not yet offer voice interaction. This study introduces VoiceBack, an artificial intelligence (AI)-driven voice-based feedback system conceptualized to support both customers and online travel agencies during the booking process. It proposes a theoretically and empirically underpinned design concept that involves a voice user interface (VUI) for customer feedback. This feedback, collected by an AI agent, is analyzed and converted into actionable statistics, which are then presented to online travel agencies through a visual interface. The interface is designed to highlight problem areas and usability issues during the booking process. This study contributes to the field of human-centered AI, by offering insight into the complex process of designing and integrating voice, emotion, and feedback within user interfaces. This integrated approach can enrich the user experience of customers when booking travel online, and pave the way for more intuitive and responsive interaction designs in the future.

Within Clinic Reliability and Usability of a Voice-Based Amazon Alexa Administration of the General Anxiety Disorder 7 (GAD 7).

This is the second in a series of studies assessing the usability and reliability of a novel voice-based delivery system of mental health screening assessments. The previous study demonstrated the reliability and patient preference of a voice-based format of the Patient Health Questionnaire 9 (PHQ 9) for measuring major depression compared to a traditional paper format. Through this study, we further examined the Amazon Alexa tool in the administration of the General Anxiety Disorder 7 (GAD 7). With a replicated methodology to the first study, 40 newly administered patients completed the GAD 7 in one format at their first session and the alternate format at their follow up. Results from the new in clinic population replicated the findings observed in the first PHQ 9 study: GAD 7 assessment scores for the Alexa and paper version showed a high degree of reliability (α = 0.77), patients showed higher overall positive attitudes for the voice-based GAD 7 format, and subscales for attractiveness, stimulation, and novelty were significantly higher for the voiced-based format. Results also demonstrated 42 (84%) of the 50 patients who completed the voice-based format responded as being willing to use the device from home. With new recommendations of universal screening of anxiety disorders for patients below the age of 65 and rapid changes in virtual mental healthcare, convenient screenings are more important than ever. We believe this novel clinical assessment tool has the potential to improve patient behavioral healthcare while mitigating the workload of healthcare professionals.

Voice-Based Navigation System for Visually Impaired Using Ultrasonic and Moisture Sensor via Bluetooth and GPS Tracker

This is a project on the development of a voice-based navigation system to help the visually impaired travel independently and safely. All the modules integrated together work on ultrasonic sensors for obstacle detection and moisture sensors to identify slippery surfaces and hence ensure a safer walk. It embeds Bluetooth technology, supporting real-time voice assistance that gives the user audio cues and directions. The GPS tracker with an emergency button adds location-tracking functionality to the system, along with a fast alert mechanism in case of emergency. Combinations of all these modules can be used to make a single, integral solution for mitigating frequent mobility challenges of visually impaired persons. It is efficient and reliable, showing improvements in quality of life and safety for the blind community after testing in various scenarios.

D-SCAN : DEPRESSION DETECTION

Depression is a serious illness that affects millions of people globally. From child to senior citizen are facing depression. Major area is occupied by adults, college going students and teenagers also. In recent years, the task of automation depression detection from speech has gained popularity. We provide a comparative analyses of various features for depression detection by evaluating how a system built on text-based, voice-based, and speech-based system. Detecting texts that express negativity in the data is one of the best ways to detect depression. In this paper, this problem of depression detection on social media and various machine learning algorithms that can be used to detect depression have been discussed. Key Words: Depression, Face detection, Audio detection, Video detection, Healthcare innovation, Result.

Design and Construction of Voice Controlled Home Automation using Arduino

System automation has been widely researched in the twenty-first century due to its essential role in daily life. The fundamental advantage of an automated system is its ability to reduce human stress and minimize errors. Over the past few years, there has been a swift shift from traditional switches to switches equipped with remote controls. Currently, the presence of conventional wall switches distributed around the house poses challenges in terms of use, especially for individuals who are elderly or have physical disabilities. Due to technological advancements, mobile smartphones are now affordable for all individuals. Android devices are becoming equipped with applications that aid in multiple ways. Another new technology is the Google speech recognition APIs, which enable voice-based system command and control. This study demonstrates the implementation of voice-controlled home automation using the Arduino Uno microcontroller. Users of this system will be able to exercise full authority over every domestic device through spoken commands. The control circuit consists of an Arduino Uno microcontroller that receives and interprets voice commands from an Android smartphone equipped with the corresponding application. While the Bluetooth module shares signal data after establishing a wireless link between the microcontroller and the smartphone, the relay regulates device switching.

Voice-Based Email System for Visually Impaired

Voice-Based Email System for Visually Impaired

Enhancing Email Accessibility for Visually Impaired Individuals

This paper presents an innovative, voice-based email system designed to improve email accessibility for visually impaired individuals. The proposed system leverages Artificial Intelligence and speech recognition technologies to convert speech to text and text to speech, enabling visually impaired individuals to send and receive emails using voice commands. The system offers an intuitive user interface, secure authentication measures, and robust database architecture to ensure seamless and secure user experience. Comparative analysis with traditional email systems reveals the superior functionality and inclusivity of the proposed system. Despite certain limitations, future enhancements promise to further refine the system, paving the way for a more inclusive digital communication environment.

Voice-based e-mail for Information systems: An aid to visually impaired

Artificial intelligence has the potential to revolutionize the way that visually impaired individuals interact with technology. With this in mind, a voice-based email system for visually impaired individuals has been proposed as a solution to provide a convenient and accessible way of managing email. The system leverages advanced Natural language processing (NLP)and Automatic Speech Recognition(ASR) technologies to convert spoken commands into email actions. The system supports voice commands for dictating emails, text-to-speech functionality for reading emails, and speech-to-text for writing emails, navigating the inbox, giving the count of unseen emails, and managing emails. This system is designed to be user-friendly, intuitive, and accessible, ensuring that blind individuals can easily navigate and use it with ease. Implementation of this system has the potential to greatly improve the daily lives of visually impaired individuals by providing a more convenient and accessible way to manage emails. This project presents an automation system for AI-powered voice-based email designed specifically information passing system to help blind individuals.

Enhance Voice-Based Email Web System for Visually Impaired People

In today's world, communication has become terribly simple thanks to the combination of communication technology and also the Internet. Email is one of the widely used ways of communication. However, it is difficult for the visually impaired to use this technology because it requires visual perception. Although many new advances have been made in the effective use of computers, no naive users without visual impairments can use this technology as effectively as ordinary naive users. Thus, in this study, firstly we review all the existing voice-based email systems whether it’s desktop applications, websites, or mobile applications, and found some drawbacks and flaws. After that, we present our improved voice-based email system that will help even a naïve visually impaired person to use the services for communication. The system will not let the user make use of the keyboard and mouse instead will work only on voice operations and speech conversion to text. The developed system uses the PBKDF2 algorithm with SHA256 hash and provides better security while storing passwords. Also, this system can be used by any normal person. The system allows the normal user to choose between voice and normal operations to manage time efficiently. The system we developed is completely based on interactive voice response that’s why it is user-friendly and efficient to use.

Vision Based Banknote Recognition System

Abstract: People who are visually impaired face great difficulties in recognizing banknotes for day-to-day transactions as the texture and shape of many banknotes are very similar. Also, the Indian currency system does not have a separate banknote in circulation that might help people who are visually disabled. This paper presents a real-time Indian currency detection system for visually impaired persons. The proposed work makes use of the vision-based system to facilitate the visually impaired people to prosperously recognize banknotes. In this paper, a recognition system is implemented by making use of various machine learning and deep learning approaches which can produce an accuracy of up to 90%. In this system, totally two experiments are carried out on the banknote’s image. The first one is the analysis of the different regions of the banknote, the second experiment is the examination of the banknote image which was captured using a camera in a regulated environment. Our system is extended to support the visually impaired people by executing a “Voice-based assistance system” which would help us in giving the voice output. This system can identify all the seven banknotes used in India and exhibit the result with both textual and auditory output. People who are visually impaired will be able to easily use it in daily transactions.

Within Clinic Reliability and Usability of a Voice-Based Amazon Alexa Administration of the Patient Health Questionnaire 9 (PHQ 9).

Over the last two decades, metric-based instruments have garnered popularity in mental health. Self-administered surveys, such as the Patient Health Questionnaire 9 (PHQ 9), have been leveraged to inform treatment practice of Major Depressive Disorder (MDD). The aim of this study was to measure the reliability and usability of a novel voice-based delivery system of the PHQ 9 using Amazon Alexa within a patient population. Forty-one newly admitted patients to a behavioral medicine clinic completed the PHQ 9 at two separate time points (first appointment and one-month follow up). Patients were randomly assigned to a version (voice vs paper) completing the alternate format at the next appointment. Patients additionally completed a 26-item User Experience Questionnaire (UEQ) and open-ended questionnaire at each session. Assessments between PHQ 9 total scores for the Alexa and paper version showed a high degree of reliability (α = .86). Quantitative UEQ results showed significantly higher overall positive attitudes towards the Alexa format with higher subscale scores on attractiveness, stimulation, and novelty. Further qualitative responses supported these findings with 85.7% of participants indicating a willingness to use the device at home. With the benefit of user instruction in a clinical environment, the novel Alexa delivery system was shown to be consistent with the paper version giving evidence of reliability between the two formats. User experience assessments further showed a preference for the novel version over the traditional format. It is our hope that future studies may examine the efficacy of the Alexa format in improving the at-home clinical treatment of depression.

Comparative Analysis and Development of Voice-based Chatbot System for Differently-abled

One technology that improved humans’ lifestyle is a Chatbot System, an AI-based system that conducts people’s conversations. Chatbots are used in a wide range of applications-assistive technologies, customer service, home automation, education, medical bots, entertainment, etc. Such technology could be beneficial to differently-abled for teaching, assistance, etc. But when it comes to people with a slight speech disorder or autism, available chatbot systems aren’t very effective. This paper investigates the existing speech recognition APIs based on WER and CER and tries to improve results by adding a personalized layer for the user. This chatbot system can be embedded with existing technologies-domestic robots, smart mirrors, home automation, medical applications, etc. It will open these technologies to a wide range of audiences. The proposed Chatbot will use the existing speech recognition API and improve the results based on the above performance measures.

Voice-based control system for smart hospital wards: a pilot study of patient acceptance

BackgroundThe smart hospital's concept of using the Internet of Things (IoT) to reduce human resources demand has become more popular in the aging society.ObjectiveTo implement the voice smart care (VSC) system in hospital wards and explore patient acceptance via the Technology Acceptance Model (TAM).MethodsA structured questionnaire based on TAM was developed and validated as a research tool. Only the patients hospitalized in the VSC wards and who used it for more than two days were invited to fill the questionnaire. Statistical variables were analyzed using SPSS version 24.0. A total of 30 valid questionnaires were finally obtained after excluding two incomplete questionnaires. Cronbach’s α values for all study constructs were above 0.84.ResultWe observed that perceived ease of use on perceived usefulness, perceived usefulness on user satisfaction and attitude toward using, and attitude toward using on behavioral intention to use had statistical significance (p < .01), respectively.ConclusionWe have successfully developed the VSC system in a Taiwanese academic medical center. Our study indicated that perceived usefulness was a crucial factor, which means the system function should precisely meet the patients' demands. Additionally, a clever system design is important since perceived ease of use positively affects perceived usefulness. The insight generated from this study could be beneficial to hospitals when implementing similar systems to their wards.

Voice Controlled Home Automation Using AI and NLP

The aim of home automation is to make our lives easier and to improve the quality of life. The concept of Smart Homes builds on the progressing maturity of areas such as Artificial Intelligence and Natural Language Processing. Here, natural language processing (NLP) plays a vital role since it acts as an interface between human interaction and machines. Through NLP users can either command or control devices at home even though disabled persons command or request varies from presets. An application area of AI is Natural Language Processing (NLP). Voice assistants incorporate AI using cloud computing and can communicate with the users in natural language. Voice assistants are easy to use and thus there are millions of devices that incorporate them in households nowadays. Our project aims at providing a fully automated voice based solution that our users can rely on, to perform more than just switching on/off the appliances. The user sends a command through speech to the mobile device, which interprets the message and sends the appropriate command to the specific appliance. The primary objective is to construct a useful voice-based system that utilizes AI and NLP to control all domestic applications and services and also learn the user preferences over time using machine learning algorithms.

Smart Home Automation—Use Cases of a Secure and Integrated Voice-Control System

Smart home automation is expected to improve living standards with the evolution of internet of things (IoT) that facilitate the remote control of residential appliances. There are, however, several factors that require attention for broader successful consumer adoption. This paper focusses on three key barriers: (i) different underlying technologies requiring an integrated voice-based control for ease of use, (ii) lack of trust due to security and privacy concerns, and (iii) unawareness of the use of machine intelligence by users for exploiting the full potential of smartness. Voice-controlled home environments are possible with cloud-based solutions that are being deployed commercially. However, there are drawbacks due to non-standard voice channels and commands with delays in meeting the required response time for real-time services. Adoption is also required to meet with the expected goals of simplicity, security, and integration. To address these barriers, we propose a model integrating IoT services and wireless technologies for developing a secure smart home automation with a voice-controlled artificial intelligence system. We demonstrate the model’s application in a variety of practical use cases, by implementing a secure and smart voice-based system for an integrated control of several home devices seamlessly.

VOICE BASED EMAIL FOR BLIND

Now-a-days internet has become one of the basic aids for day-to-day living. Every human being is widely accessing the knowledge, information and also using for communication through internet. However, blind people face difficulties in accessing these net-based information, also in using any service provided through internet. The advancement in computer based accessible systems has opened up many possibilities for the visually impaired across the worlds in a wide way. Audio based virtual environment like, the screen readers and many voice-based search engines have helped Blind people to access internet applications immensely. We describe the Voice-based mail system architecture that can be used by a Blind person to access e-Mails easily and efficiently. The contribution made by this research has enabled the Blind people to send and receive voice-based e-Mail messages with the help of a computer.

IFDDS: An Anti-fraud Outbound Robot

With the rapid growth of internet finance and e-payment, payment fraud has attracted increasing attention. To prevent customers from being cheated, systems often block risky payments depending on a risk factor. However, this may also inadvertently block cases which are not actually risky. To solve this problem, we present IFDDS, a system that proactively chats with customers through intelligent speech interaction to precisely determine the actual payment risk. Our system adopts imitation learning to learn dialogue policies. In addition, it encompasses a dialogue risk detection module which identifies fraud probability every turn based on the dialogue state. We create a web-based user interface which simulates a practical voice-based dialogue system.

Automatic Voice-Based Recognition For Automotive Headlights Beam Control

Driving comfort plays an important role in modern automotive technologies. One of the ways of comforting the driver is the voice-based recognition to control car headlights. The driver uttered a ‘specific word’ that is taken as an input to the proposed voice-based recognition system. The proposed mechanism then determines if the signal was either ‘high beam’ or ‘low beam’ to control the car headlights. To activate the headlight’s beam, this voice recognised signal is sent to a processing board. Mel Frequency Cepstral Coefficient (MFCC) is used in the recognition mechanism to extract the uttered word before being fed into Artificial Neural Networks (ANN) and Support Vector Machines (SVM) as a classification engine. The proposed automatic voice-based recognition was evaluated via experimental work. The results show that the proposed automatic voice-based recognition for headlights activation control involving MFCC feature works effectively in which SVM gives slightly better performance accuracy when compared to ANN. In addition to a lesser training time, the resulting accuracy using SVM in the training and testing phase is 93.595% and 91.74% respectively. Meanwhile, ANN has an accuracy of 89.39% and 88.16% in the training and testing respectively.

Development of a regional voice dataset and speaker classification based on machine learning

At present, voice biometrics are commonly used for identification and authentication of users through their voice. Voice based services such as mobile banking, access to personal devices, and logging into social networks are the common examples of authenticating users through voice biometrics. In Pakistan, voice-based services are very common in banking and mobile/cellular sector, however, these services do not use voice features to recognize customers. Therefore, the chance to use these services with false identity is always high. It is essential to design a voice-based recognition system to minimize the risk of false identity. In this paper, we developed regional voice datasets for voice biometrics, by collecting voice data in different local accents of Pakistan. Although, there is a global need for voice biometrics especially when voice-based services are common, however, this paper uses Pakistan as a use case to show how to build regional voice dataset for voice biometrics. To build voice dataset, voice samples were recorded from 180 male and female speakers with two languages English and Urdu in form of five regional accents. Mel Frequency Cepstral Coefficient (MFCC) features were extracted from the collected voice samples to train Support Vector Machine (SVM), Artificial Neural Network (ANN), Random Forest (RF) and K-nearest neighbor (KNN) classifiers. The results indicate that ANN outperformed SVM, RF and KNN by achieving 88.53% and 86.58% recognition accuracy on both datasets respectively.