Voice-activated Control Research Articles

Exploring antecedents impacting user satisfaction with voice assistant app: A text mining-based analysis on Alexa services

The Amazon Alexa app is one of the most widely used voice assistant apps to manage customer information-seeking behavior and voice shopping. It provides companionship to the visually impaired and senior citizens. There has not been significant empirical evidence focusing on the determinants of user satisfaction with the voice assistant app. Therefore, this study proposed ten user satisfaction antecedents for the Amazon Alexa app based on 13,363 online user reviews. The Latent Dirichlet Allocation (LDA) technique, regression analysis, dominance analysis, and correspondence analysis were used to analyze these reviews. The regression analysis revealed ten user satisfaction predictors of the Amazon Alexa App. The voice shopping experience with the Alexa app aids caregivers in catering to the needs of elderly individuals by providing convenient shopping, voice-activated control, reminders, smart home integration, and access to information. The result of the dominance analysis shows personal assistance and app update are the most important factors for predicting user satisfaction with the VA app. Moreover, personal assistance and voice-controlled automation experience are the most frequent topics for senior citizens and blind people. The findings of this study can provide valuable insights for business managers in determining the prioritization of key determinants of user satisfaction and offering new competitors a competitive edge in the voice assistant market.

A voice activated bi-articular exosuit for upper limb assistance during lifting tasks

Abstract Humans are favoured to conventional robotics for some tasks in industry due to their increased dexterity and fine motor skills, however, performance of these tasks can result in injury to the user at a cost to both the user and the employer. In this paper we describe a lightweight, upper-limb exosuit intended to assist the user during lifting tasks (up to 10kg) and while operating power tools, which are common activities for industrial workers. The exosuit assists elbow and shoulder flexion for both arms and allows for passive movements in the transverse plane. To achieve the design criteria an underactuated mechanism has been developed, where a single motor is used to assist two degrees of freedom per arm. In the intended application, the hands are generally busy and cannot be used to provide inputs to the robot, therefore, a voice-activated control has been developed that allows the user to give voice commands to operate the exosuit. Experiments were performed on 5 healthy subjects to assess the change in Muscular Activation (MA), inferred through Electromyography (EMG) signals, during three tasks: i) lifting and releasing a load; ii) holding a position and iii) manipulating a tool. The results showed that the exosuit is capable of reducing EMG activity (between 24.6% and 64.6%) and the recognition rate (94.8%) of the voice recognition module was evaluated.

Program Hierarchical Realization of Adaptation Behavior of the Cognitive Mobile Robot with Imitative Thinking

Now rapid development of research and development in the area the androidnykh (anthropomorphous) robots is abroad observed. In the modern options such robots are equipped with the control system including: system of technical vision, system of voice-activated control and system of voice messages, tactile system, system of dimensional orientation, control system of a gait and stability, control system of behavior. The most practical designs of such robots are developed in Japan. They are called humanoid robots as are similar to the person not only in a form, but also, to some extent, on behavior. A number of such robots is developed for commercial application: Asimo (Honda), SDR-4X (Sony), Hoap-2 (Fujitsy). PETMAN – robot - android, (Boston Dynamics) Possibilities of anthropomorphous robots are defined by their design and a control system. When developing prototypes of humanoid robots special attention should be paid to development of the system of management which defines an athletic and behavioural ability of robots. The complexity of behavior of mobile robots results in need of searching of nonconventional paths of creation of their control systems. One of such paths consists in use of the principles of the organization of nervous system of the person disclosed by the modern psychology and a neurophysiology. The behavior of the robot described in article is realized by the functional hierarchical system of controllers, similar to a control system of behavior of a human body. The behavior arises under the influence of informational requirement on which imitative thinking determines orientation in a situation by models of the external environment and behavior. Orientation comes to the end with the choice of the corresponding line-up of subprograms of hierarchical system of controllers which realization leads to realization of behavior. Subprogrammes of actions of behavior of robots are set in programming languages.

A study of the user interface for a surgical navigation system using voice-activated control

A study of the user interface for a surgical navigation system using voice-activated control

About neural-network algorithms application in viseme classification problem with face video in audiovisual speech recognition systems

The paper considers the phoneme recognition by facial expressions of a speaker in voice-activated control systems. We have developed a neural network recognition algorithm by using the phonetic words decoding method and the requirement for isolated syllable pronunciation of voice commands. The paper presents the experimental results of viseme (facial and lip position corresponding to a particular phoneme) classification of Russian vowels. We show the dependence of the classification accuracy on the used classifier (multilayer feed-forward network, support vector machine, k-nearest neighbor method), image features (histogram of oriented gradients, eigenvectors, SURF local descriptors) and the type of camera (built-in or Kinect one). The best accuracy of speaker-dependent recognition is shown to be 85% for a built-in camera and 96% for Kinect depth maps when the classification is performed with the histogram of oriented gradients and the support vector machine.

Integrated operation systems and voice recognition in minimally invasive surgery: comparison of two systems

Integrated operation systems were developed for centralization and easy control of all components within the operating room (OR). These systems represent central units that use communication technology to connect and control various components of the OR. Voice control that is independent of the speaker has been a pioneering innovation in the central control of different OR components. The aim of the present study was to evaluate the utility of two voice-activated control systems, the Siemens Integrated OR System (SIOS, Siemens Medical Solutions, Siemens AG) and the OR1 (Karl Storz GmbH & Co. KG), for delivery of commands to specific OR equipment. To compare the two systems, actions such as adjusting the operating table, increasing gas pressure, switching on the video recorder, and controlling the endolight source were defined according to a study protocol. These actions were to be executed by test persons through speech and manual control after a suitable training period. The parameters evaluated were training time, time to execute each action, number of repeated commands, and number of functional errors. Seventy-four test persons from five nations were selected to participate. The numbers of repeated commands and functional errors differed significantly between systems in all user groups in favor of the SIOS (mean repeated commands for surgeons: SIOS, 2.4; OR1, 14.7, p < 0.0001). The SIOS voice control was more effective and more reliable than that of the OR1. Importantly, unlike the OR1, the SIOS produced no functional errors. The appropriate conditions for greater acceptance of these systems must be considered, together with additional technical improvements and possible combinations of advantages of the available systems.

Utility of a Voice-Activated System in Minimally Invasive Surgery

Advances in computer enhancements for surgery, including a voice-activated control system for minimally invasive surgery, are being introduced into clinical practice. Few reports have objectively evaluated the utility of the voice-activated control system. The aim of this study was to evaluate the utility of a voice-activated control system for delivery of commands to specific operating room (OR) equipment. We evaluated a total of 30 laparoscopic procedures: 15 laparoscopic hernia repairs, 10 laparoscopic cholecystectomies, and 5 laparoscopic fundoplications performed with the HERMEStrade mark Operating Room Control Center (Computer Motion, Santa Barbara, California) voice-activated control system. When the voice command (VC) to the HERMES system was given, the circulating nurse was observed and her location was recorded. The 3 locations were A, the nurse was immediately available in the OR, not engaged in any other tasks; B, the nurse was in the OR but engaged in other tasks; or C, the nurse was outside the OR. The 30 cases were performed by the same surgeon and completed laparoscopically. For 170 VCs for gas insufflation, the location of the circulating nurse was: A=50, B=98, and C=22. For 135 light source adjustments, the locations were A=34, B=82, and C=19. In 76 white balance VCs: A=16, B=51, and C=9. In 128 VCs for camera adjustment: A=27, B=77, and C=24. Eight video capture VCs: A=1, B=3, and C=4. For 69 image capture VCs: A=5, B=41, and C=23. The total number of VCs was 586: A=133 (22.7%), B=352 (60%), and C=101(17.3%). All VCs were accurately interpreted by the HERMES system. Voice-activated control systems improve communication with and efficiency of OR staff. The surgeon is afforded the most timely equipment adjustment possible. Circulating nurses are allowed to concentrate on patient care instead of equipment adjustment during the course of the surgery.

The Potential Reduction in Musculoskeletal Injury in the Nonscanning Arm by Using VoiceScan Technology During Sonographic Examinations

Between 84% and 93% of sonographers in North America and Australia have reported musculo-skeletal injuries related to their work activities. One type of occupational injury affects the non-scanning arm as sonographers reach for the control panel to manipulate the controls of the ultrasound equipment. A number of factors contribute to the reduction of these injuries, including improved ergonomic equipment designs. An important ergonomic design that targets the operator’s nonscanning arm is a voice-activated control panel. The goals of this study were (1) to test the alternate hypothesis that there is significant difference in muscle activity of the upper trapezius muscle between three positions of forward flexion of the nonscanning arm and (2) to determine the efficacy of using voice activation technology to reduce the muscle activity required by the nonscanning arm to manipulate the keyboard of the ultrasound equipment.

Voice-activated control for electrical device

An apparatus for voice-activated control of an electrical device comprises a receiving arrangement for receiving audio data generated by user. A vioce recognition arrangement is provided for determining whether the received audio data is a command word for controlling the electrical device. The voice recognition arrangement includes a microprocessor for comparing the received audio data with voice recognition data previously stored in the voice recognition arrangement. The voice recognition arrangment generates at least one control signal based on the comparison when the comparison reaches a predetermined threshold value. A power control controls power delivered to the electrical device. The power control is responsive to at least one control signal generated by the voice recognition arrangement for operating the electrical device in response to the at least one audio command generated by the user. An arrangement for adjusting the predetermined threshold value is provided to cause a control signal to be generated by the voice recognition arrangement when the audio data generated by the user varies from the previously stored voice recognition data.

The Influence of In-Vehicle Noise on Speech Recognition for Automotive Voice-Activated Control Systems

Voice activation provides a safe and convenient method of controlling vehicle systems such as in-car entertainment, telecommunications and climate control. In the fullness of time it is likely that there will be a high demand across all vehicle classes for such systems for a wide range of vehicle control functions. One of the challenges facing their development and introduction into vehicles is that of the in-vehicle noise environment.

User Interface Design for Maintenance/Troubleshooting Expert System

Expert systems applications for special environments impose special requirements on the user-system interface. A study was conducted to determine requirements and define a design concept for the interface for an expert system being developed to support corrective maintenance and troubleshooting of gas turbine electronic equipment and controls. The resulting design specifies a portable unit containing color flat panel video/graphics display, special function membrane keypad, miniature printer, and headset with voice input/output. Communication with the expert system is structured by multiple-window information presentation and voice-activated control functions.