Deep Learning Approach for Protecting Voice-Controllable Devices From Laser Attacks

The laser-based audio signal injection can be used for attacking voice controllable systems. An attacker can aim an amplitude-modulated light at the microphone's aperture, and the signal injection acts as a remote voice-command attack on voice-controllable systems. Attackers are using vulnerabilities to steal things that are in the form of physical devices or the form of virtual using making orders, withdrawal of money, etc. Therefore, detection of these signals is important because almost every device can be attacked using these amplitude-modulated laser signals. In this project, the authors use deep learning to detect the incoming signals as normal voice commands or laser-based audio signals. Mel frequency cepstral coefficients (MFCC) are derived from the audio signals to classify the input audio signals. If the audio signals are identified as laser signals, the voice command can be disabled, and an alert can be displayed to the victim. The maximum accuracy of the machine learning model was 100%, and in the real world, it's around 95%.

Appliance Control with IOT-Arduino of Voice Command Detection for Mobility Impaired People

People with physical mobility disabilities experience limited ability to perform daily routine. Integration between home appliances and Internet of Thing (IoT) can be used to support these people. The technology allows tasks to be performed much more easily and enable access to applications and services that would be a challenge with existing digital user interfaces. However, the developed system that is commercially available is costly and equipped with highly specific interfaces which may require considerable technical competency to conduct system interfacing. The purpose of this study is to develop a low cost IOT system for voice-enabled lamp control by utilizing Google Assistant that is available in commercial Android based mobile devices, allowing user to operate lighting appliances without moving. Personal assistance using Google platform embedded with Arduino microcontroller, ESP8266-based NodeMCU development board and integrated Blynk application allow for remote monitoring capability. The system is remotely controlled from a tablet or smartphone to assist disabled people with restricted mobility, in particular those with lower limb disabilities. The system had been tested and demonstrated that the lamp control can be easily accessed by voice command that is then validated using voice pitch analyzer. Test result indicated that capability of the integrated voice control system is verified up to a maximum distance of 24.5 meter, making it a potential implementation in any customized smart home or room system for people with mobile disability.

Voice Controlled Guided System for Wheelchair with Collision Detection and Avoidance

Many people are suffering from temporary or permanent disabilities due to accidents or any pre-illness that may introduce a wheelchair for the person as essential. The use of a wheelchair independently can be derived from the severity of the disability. But in the case of severe situations when a person relies on somebody else to handle the movement of a wheelchair. This paper aims to provide a solution to this problem by using voice command to guide the wheelchair eliminating the reliability of another person.

Pengembangan Aplikasi Asisten Pintar Pembuka Al Qur’an 30 Juz dengan Perintah Voice Command

Many developers of digital Qur'an applications today still use tap to scrolling to run applications, although the features are interesting. This makes it less effective and efficient in opening the Qur'an. As is the case during the taklim assembly, some da'i are very interactive with jama'ah, asking to open certain surahs and verses so that there are some who have difficulty in searching. Therefore, the need for the Qur'anic application with voice command command to facilitate users. This research is the development of the Qur'an application with voice recognition feature. Using the waterfall method in development, voice command with google speech API as a voice command of surah and verse calling in the Qur'an application 30 juz. Conducted 10 randomized experiments with calls in the form of play or open surahs and certain verses give a 90% accuracy result. Commands can be given when online or offline. Then the use of google speech API can be very useful for use in the development of other applications.

Anti-Spoofing Voice Commands

This paper presents an anti-spoofing design to verify whether a voice command is spoken by one live legal user, which supplements existing speech recognition systems and could enable new application potentials when many crucial voice commands need a higher-standard verification in applications. In the literature, verifying the liveness and legality of the command's speaker has been studied separately. However, to accept a voice command from a live legal user, prior solutions cannot be combined directly due to two reasons. First, previous methods have introduced various sensing channels for the liveness detection, while the safety of a sensing channel itself cannot be guaranteed. Second, a direct combination is also vulnerable when an attacker plays a recorded voice command from the legal user and mimics this user to speak the command simultaneously. In this paper, we introduce an anti-spoofing sensing channel to fulfill the design. More importantly, our design provides a generic interface to form the sensing channel, which is compatible to a variety of widely-used signals, including RFID, Wi-Fi and acoustic signals. This offers a flexibility to balance the system cost and verification requirement. We develop a prototype system with three versions by using these sensing signals. We conduct extensive experiments in six different real-world environments under a variety of settings to examine the effectiveness of our design.

Controlling Led by Voice Command, Timer and Human Presence Detection

This paper focuses on the concept of home automation using arduino kit via mobile app. This paper describes and gives the direction for Arduino controlled light-weight bulb through PIR motion detector, voice commands as well as using buttons. We tend to use the PIR motion detector to get the presence of somebody's body to ON the bulb keep with the output of the motion detector. This can be used in very little areas like storerooms. We are in a position to place the motion detector at the door of house and once someone can enter the room, the motion detector will discover it and light-weight will get ON. The PIR motion detector can discover the shape up to seven meters so it's sensible for little rooms. This project additionally permits light automation by sensing the human presence inside the required varies.

Rancang Bangun Sistem Smart Locker Menggunakan Voice Access Berbasis Arduino Mega

The importance of security makes everyone must ensure the security of everything that is included in him, both from the activities and assets he owns. The value of an asset has an incentive for everyone to implement a security system as protection. One of them is in the locker cabinet which generally still uses a manual locking system. So a Smart Locker is needed that uses microcontroller technology and a GSM Module combined with supporting applications such as Android-based. The purpose of this research is to design a security system with locker cabinet doors using Arduino Mega-based Voice Access. When the locker is forced to be opened, the buzzer will notify the owner that the locker door is opened via SMS short message remotely and the GSM module aims to open and lock the locker door via SMS message remotely where SMS communication mode uses the GSM module. Voice Access aims to make your access rights when you want to activate the locker system using the system voice command On and Off. Not everyone can use this locker because only a few can use it with the access given by entering the correct password when opening the locker door. The locker lock can be unlocked if the password is entered correctly, then the password is successful and then it will be stored and displayed on the LCD screen as an interface.