Voice Recognition Technology Research Articles

스마트 스피커와의 상호작용성, 의사소통 효능감, 이용자 태도 간의 구조적 관계에 관한 연구

Smart speaker is one of the most popular machines which applies voice recognition technology. Since smart speaker users highly interact with the machine, we suggest that smart speaker-user interactivity has positive effects on users’ satisfaction and loyalty. We also identify the effect of communication efficacy as a mediator of this relationship. Findings show that the two dimensions of interactivity(active control and synchronicity) both have a significant effect on user satisfaction, and satisfaction also showed significant effect on users’ loyalty for a smart speaker. Results also indicate that communication efficacy significantly mediates the relationship between smart speaker-user interactivity(active control and synchronicity) and user attitude(satisfaction and loyalty). Our findings suggest that a highly interactive smart speaker is expected to have competitive advantage in the market since it enhance users’ communication efficacy, leads to high user satisfaction, and consequently loyalty.

Research on the application of intelligent speech recognition technology in medical big data fog computing system

ABSTRACT Through the establishment of a voice database and voice recognition model, combined with voice recognition processing methods, an intelligent voice recognition input system with medical big data and fog computing as the scene is developed to realise the application of intelligent voice recognition technology in the system, which can reduce the medical staffdaily burden, reduce repetitive workload, and improve the quality and efficiency of clinical work. Based on the key technologies of intelligent voice recognition and medical big data, combined with the characteristics of fog computing, the development of electronic medical records and examination reports intelligent voice entry, mobile nursing intelligent voice entry, non-contact intelligent voice data interaction system, through the construction of fog computing model, design and develop an intelligent medical system to realise the rapid input and output of medical records and examination reports, reduce the workload of doctors and nurses, and concentrate their limited time on the treatment process itself. At the same time, according to the working characteristics of different medical departments, the intelligent system design adopts convenient, practical and efficient intelligent speech recognition technology application tools, and makes full use of big data technology and fog computing architecture to improve speech recognition rate, reduce network delay, and improve query efficiency, It is beneficial to assist the work of various clinical departments, better improve the treatment effect and innovate new medical models.

Using Voice Recognition in E-Learning System to Reduce Educational Inequality During Covid-19

During the COVID -19 pandemic, educational institutions around the world faced problems that have to do with the frustration of students for whom traditional education has been replaced by the online format. Students are experiencing technical difficulties in the digitalization of education. International monitoring of education systems has shown that quite a few countries were ready to move to distance learning, both for technical and economic reasons. The covid pandemic has caused an increase in educational inequality. Elearning systems were expected to reduce inequality in education, but empirical research has shown that learning in this format not only does not reduce, but can increase inequality, increasing the gap in educational outcomes between students with different socioeconomic status. The article describes applications of using voice recognition technology based on artificial intelligence which, by our opinion, may reduce educational inequality during covid-19. We presented a comparative analysis of existing examples artificial intelligence in the educational process. Artificial intelligence uses in specialized software it makes educational process more convenient for both the students and the teachers. There is a description of an application “Academic phrase bank" developed by author. The application consists of two specialising actions for Google assistant. The application allows to increase academic vocabulary, train of creating grammatically correct academic expressions, and memorize templates of academic phrases. In active mode, this application helps to create correct phrases of academic English and improve the abilities of understanding English speech.

RETRACTED ARTICLE: Application of embedded voice recognition technology and internet of things in music interactive teaching system

RETRACTED ARTICLE: Application of embedded voice recognition technology and internet of things in music interactive teaching system

Voice Recognition Technology : A Review

Recent advances in computing technology have made voice recognition is a — a biometric technology based on the unique characteristics of a person's voice — more convenient, safer, and secure than ever before. After years of research and development, one of the major research challenges remains the accuracy of automatic speech recognition (eg., variations of the context, speakers, and environment). In this paper, We have review the current state of voice recognition. Finally, we look at possible industrial applications for voice recognition technology, such as public safety solutions.

A Study on the Standardization of Service Process in Silver Town of Smart City

초고령화 시대를 맞이하고 있는 우리나라의 경우 인구고령화에 따라 고령인구를 위한 실버산업이 부상하고 있다. 본 연구는 우리나라 실버산업 중 사업의 성과를 나타낸 ‘실버타운’을 연구대상으로 하였다. 국내 실버타운에 대한수요는 점차 증가하고 있지만 높은 분양가로 인해 노인들이 쉽게 접근하기 어려운 실정이다. 또한, 4차 산업혁명시대가 도래하면서 실버산업은 ICT, 5G, Big Data, IoT 등 다양한 신기술이 접목된 스마트화한 산업으로 변화가 필요하며 이러한 수요에 대응할 필요가 있다. 따라서, 본 연구에서는 4차 산업혁명시대의 실버타운 서비스 프로세스를 표준화함으로써 실버타운의 수요 증가에 대응하고 신기술이 접목된 새로운 실버타운의 서비스 프로세스모델을 제시하고자 하였다. 이를 위해 우리나라 실버타운 업체가 제공하는 서비스의 프로세스를 조사한 후, 텍스트마이닝 기법을 활용하여 서비스 단계별로 나타난 단어별 빈도수를 추출한 후, 공통적인 서비스 요소를 도출하여 실버타운 서비스 프로세스를 설계하고 통일하였다. 통일된 5가지 서비스(의료건강, 식사, 생활편의, 안전관리, 문화여가)에 ‘KS S 2028-1 노인요양시설 서비스 표준’의 입소(入所) 중 서비스 가운데, 식사 서비스, 상담 서비스, 건강관리 서비스, 여가 서비스를 인용하고, 스마트시티 구현기술 중 Big Data, ICT, 로봇, IoT, 음성인식, GPS, 인공지능 기술을 적용하여 스마트시티 실버타운 서비스 프로세스 표준 모델과 서비스 청사진을 제시하였다. 본 논문은 첫 번째로, 실버타운이 서비스를 제공을 위한 기본 자료로 활용할 수 있고, 실버타운 입소자의 서비스 선택의 기초 자료로 활용될 수 있으며, 두 번째로, 실버타운 종사자에 대한 교육자료로 활용이 가능하다. 향후 다양한 공공 서비스 프로세스의 표준화 연구 분야에 도움이 될 것으로 기대된다.In Korea, which is facing an era of super-aging, the silver industry for the elderly population is emerging as the population ages. This study is based on ‘Silver Town’ which shows business performance among the silver industries in Korea. Demand for silver towns in Korea is gradually increasing, but it is difficult for senior citizens to access them easily due to high sales prices. In addition, as the era of the Fourth Industrial Revolution arrives, the silver industry needs to be changed into a smart industry that combines various new technologies such as ICT, 5G, Big Data, and IoT, and needs to respond to this demand. Therefore, this study aimed to standardize the Silver Town service process in the era of the Fourth Industrial Revolution to respond to the increase in demand for Silver Town and present a new Silver Town service process model incorporating new technologies. To this end, the process and contents of services provided by Korean silver town companies were investigated, and the frequency of each word appeared in each service stage was extracted using text mining techniques, and common service elements were derived to design and unify the silver town service process. Five unified services (medical health, meals, living convenience, safety management, cultural leisure) cited meal services, counseling services, health care services, and leisure services during admission service to the KS 2028-1 Standard for the Service of Nursing Homes for the Elderly. Then, among the smart city implementation technologies, the smart city Silver Town service process standard model and service blueprint were presented by applying Big Data, ICT, robots, IoT, voice recognition, GPS, and artificial intelligence technologies. First, this paper can be used as a basic data when Silvertown provides services, as a basic data for Silvertown residents service choices, and secondly, it can be used as educational data for Silvertown workers, and is expected to help standardize research areas of various public service processes in the future.

Использование технологий искусственного интеллекта для дистанционного обучения

The article describes some practices of voice recognition technologies based on artificial intelligence to improve the educational process in a remote format. This is relevant to modern remote education environment. The author presents an analysis of existing approaches to the use of artificial intelligence technologies in the educational process. Elements of artificial intelligence in a specialist software make the educational process more modern and convenient both for the learner and the teacher. One of the implementations for a natural user interface is a voice-user interface, which recognizes words to understand spoken commands and to answer questions, it converts the text into speech. The author has carried out an analytical review of implementations of specialized applications for Yandex assistant in which, the voice interface is used to improve children's language skills. Algorithm development of an application for Google assistant which uses voice recognition technologies and artificial intelligence for for teaching a foreign language is described. The application can be used in the educational process for teaching academic English; it also allows to increase English vocabulary, train the construction of grammatically correct scientific expressions, and memorize scientific language patterns.

Anesthesia Innovation with AI: The Power Is Ours

Features| June 2021 Anesthesia Innovation with AI: The Power Is Ours Vesela P. Kovacheva, MD, PhD; Vesela P. Kovacheva, MD, PhD Search for other works by this author on: This Site PubMed Google Scholar Raphael Y. Cohen, BS; Raphael Y. Cohen, BS Search for other works by this author on: This Site PubMed Google Scholar Logan Scoon, MS, BS; Logan Scoon, MS, BS Search for other works by this author on: This Site PubMed Google Scholar David W. Bates, MD, MSc David W. Bates, MD, MSc Search for other works by this author on: This Site PubMed Google Scholar ASA Monitor June 2021, Vol. 85, 34–35. https://doi.org/10.1097/01.ASM.0000754260.61965.66 Views Icon Views Article contents Figures & tables Video Audio Supplementary Data Peer Review Share Icon Share Twitter LinkedIn Cite Icon Cite Get Permissions Search Site Citation Vesela P. Kovacheva, Raphael Y. Cohen, Logan Scoon, David W. Bates; Anesthesia Innovation with AI: The Power Is Ours. ASA Monitor 2021; 85:34–35 doi: https://doi.org/10.1097/01.ASM.0000754260.61965.66 Download citation file: Ris (Zotero) Reference Manager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search nav search search input Search input auto suggest search filter All ContentAll PublicationsASA Monitor Search Advanced Search Topics: disclosure, intraoperative care, patient safety, surgical procedures, operative, technology, bradycardia, infusion pumps, adoption, decision making, electronic medical records Imagine a future day at work powered by artificial intelligence (AI) technologies. Your patient that day has been risk-stratified preoperatively, and all conditions have been optimized according to the most current guidelines. As you talk to the patient, the preoperative note is updated automatically, aided by an AI voice-recognition technology. Vital signs are monitored remotely. If there is a problem with placing the I.V., the AI-enhanced ultrasound makes it a breeze. On induction, you select what medications to use, an intelligent infusion pump determines a personalized amount for the patient and titrates the doses automatically. During the operative course, EHR-integrated algorithms predict blood loss, duration of surgery, risk for complications, and suggest the best course of action for mitigation. In the PACU, care is optimized by AI models relevant to the specific type of surgery to minimize patient recovery time and to optimize pain control. Additional algorithms can further aid... You do not currently have access to this content.

Development of multilanguage voice control for smart home with IoT

Internet of Thing (IoT) is very common and demanding nowadays and home automation system is not left behind in this technology. Home automation is the concept of making any home “smart”. In this modern life, Automation is not a new thing. This technology has been using many years and normally can be seen in big companies. This automation concept can benefit our daily lives through many ways. However, the smart home technology in the market right now only support a few languages, generally English. For people who English is not their native language, it becomes a barrier in utilizing voice recognition installed in the smart home. Therefore this project will develop a Multilanguage IoT Home Automation System that focused on people who does not speak English especially elderly people in Malaysia to perform their chores routine such as turn on or turn off light by using voice commands given in their preferred language. Other than voice commands, it could be controlled wirelessly by using apps developed in the Smartphone. This system is based on Raspberry Pi and will be designed to be an affordable and reliable home automation system yet, easy to setup and use. The research focus on the methods of integrating voice recognition technology in many languages in home automation systems. This research can have a strong and positive impact to the society especially on persons with physical disabilities and older persons whom English is not their native language.

The Application of Intelligent Speech Recognition Technology in the Tone Correction of College Piano Teaching

In recent years, with the continuous deepening of college teaching reform and the rapid development of artificial intelligence, the teaching methods used in college classrooms have been greatly different from traditional ones. The original teaching programs and teaching methods need to be changed with the development of the times. The main purpose of this article is to improve the correction rate of intelligent voice recognition technology for college piano timbre without violating the safety of artificial intelligence. This article mainly conducts experiments by consulting relevant domestic and foreign literature, using observation and comparison methods, and using some neural network algorithms (BP neural network algorithm and convolutional neural network algorithm) to obtain experimental results, and finally complete our experimental goal-research intelligence The application of speech recognition technology in the tone correction of piano teaching in colleges. The test results show that the use of multiple algorithms can improve the application of intelligent speech recognition technology in the tone correction of piano teaching in colleges and universities, mainly to improve the correction rate and enhance the ability of guiding teaching.

Application Research and Implementation of Voice Control System Based on Android Speech Recognition

Based on the voice recognition technology of Android platform, combined with WiFi network communication technology and embedded control system, an audio voice control system is realized, which collects voice commands on the mobile phone APP for recognition and controls the operation of audio equipment through WiFi network and embedded control module. The voice recognition adopts the voice recognition SDK provided by IFLYTEK open platform, the WiFi network is provided by WiFi router, and the embedded control module adopts the STC15F204EA controller, which is matched with NL6621-M3WiFi module to receive processing instructions. After experimental test, the audio system can be effectively controlled by voice, which meets the requirements of modern audio equipment intelligence.

Design of life assistance device for the elderly based on artificial intelligence

With the development of the times, China has entered a stage of aging population. Because of the increase of age, the elderly are often hard to finish like bend over, squat such simple actions, which brought great challenge to the basic life of old people. Some basic activities such as walking and the toilet, are very difficult for them. In order to guarantee the basic life of the elderly, a kind of life assistance device for the elderly based on artificial intelligence is designed to help the elderly in walking and toilet. The mechanical structure of the device mainly consists of five parts, namely, walking mechanism, lifting mechanism, rotating seat cushion mechanism, rotating handrail mechanism and pulling rod backrest mechanism. The control part is mainly based on voice recognition technology. The device is simple in structure, convenient in operation and low in cost. Compared with the existing life assistance devices for the elderly, the device has more complete functions, which better solves the difficulties of the elderly in walking and using the toilet, and provides great convenience for the elderly.

Artificial intelligence and music: History and the future perceptive

Several music software programs have been developed that use AI to produce music. Like its applications in other fields, the A.I. in this case also simulates mental tasks. A prominent feature is the capability of the A.I. algorithm to learn based on information obtained such as the computer accompaniment technology, which is capable of listening to and following a human performer so it can perform in synchrony. Artificial intelligence also drives the so-called interactive composition technology, wherein a computer composes music in response to the performance of a live musician. There are several other A.I. applications to music that covers not only music composition, production, and performance but also the way it is marketed and consumed. Apart from programs that use AI to produce music, several music player programs have been developed to use voice recognition and natural language processing technology for music voice control.

Physical Activity Evaluation Using a Voice Recognition App: Development and Validation Study.

Historically, the evaluation of physical activity has involved a variety of methods such as the use of questionnaires, accelerometers, behavior records, and global positioning systems, each according to the purpose of the evaluation. The use of web-based physical activity evaluation systems has been proposed as an easy method for collecting physical activity data. Voice recognition technology not only eliminates the need for questionnaires during physical activity evaluation but also enables users to record their behavior without physically touching electronic devices. The use of a web-based voice recognition system might be an effective way to record physical activity and behavior. The purpose of this study was to develop a physical activity evaluation app to record behavior using voice recognition technology and to examine the app's validity by comparing data obtained using both the app and an accelerometer simultaneously. A total of 20 participants (14 men, 6 women; mean age 19.1 years, SD 0.9) wore a 3-axis accelerometer and inputted behavioral data into their smartphones for a period of 7 days. We developed a behavior-recording system with a voice recognition function using a voice recognition application programming interface. The exercise intensity was determined from the text data obtained by the voice recognition program. The measure of intensity was metabolic equivalents (METs). From the voice input data of the participants, 601 text-converted data could be confirmed, of which 471 (78.4%) could be automatically converted into behavioral words. In the time-matched analysis, the mean daily METs values measured by the app and the accelerometer were 1.64 (SD 0.20) and 1.63 (SD 0.20), respectively, between which there was no significant difference (P=.57). There was a significant correlation between the average METs obtained from the voice recognition app and the accelerometer in the time-matched analysis (r=0.830, P<.001). In the Bland-Altman plot for METs measured by the voice recognition app as compared with METs measured by accelerometer, the mean difference between the two methods was very small (0.02 METs), with 95% limits of agreement from -0.26 to 0.22 METs between the two methods. The average METs value measured by the voice recognition app was consistent with that measured by the 3-axis accelerometer and, thus, the data gathered by the two measurement methods showed a high correlation. The voice recognition method also demonstrated the ability of the system to measure the physical activity of a large number of people at the same time with less burden on the participants. Although there were still issues regarding the improvement of automatic text data classification technology and user input compliance, this research proposes a new method for evaluating physical activity using voice recognition technology.

Design of Smart Home Control System Based on Wireless Voice Sensor

With the rapid development of economy, science, and technology, people have higher and higher requirements for the quality of home life, and smart home systems are required to have higher convenience and comfort. The continuous development of embedded technology, short‐range wireless communication technology, and microcontroller technology provides a new development direction for the research and development of smart home systems. Under the premise of fully studying the research status and development trend of smart home systems, this paper combines embedded technology, ZigBee wireless communication technology, voice recognition technology, GSM communication technology, etc., and proposes a ZigBee‐based smart voice home appliance control system. The system adopts ZigBee wireless communication to form a comprehensive management system for household electrical appliances, electronic and electrical equipment, etc., for household electrical control, intelligent security, and environmental monitoring. This paper designs the overall scheme of a smart home control system based on voice recognition technology. According to this scheme, the hardware and software of the system are designed, and the wireless communication method combining Wi‐Fi and RF (radio frequency) of the system is also determined. In order to make the system more humane, two sets of control schemes, voice control and button control, are designed according to the system’s functional requirements. In the voice control solution, the user first reads the control commands set in the voice library on the smart terminal, and then, the system automatically recognizes the commands read by the user. After the recognition is successful, the user can control the home appliances through the command. In the key control scheme, users can control home appliances through keys on the smart terminal. The upper computer transplants the audio library and the algorithm studied in this paper to realize the audio collection and storage, the confirmation of family members, and the recognition of voice commands; the lower computer is used for real‐time collection of environmental information and wireless control of home facilities. After the system is started, the family members are first confirmed by voice, and then, the voice command recognition result and real‐time environmental information jointly decide to form a control command. The upper computer sends the control command to the lower computer through the serial port to control the corresponding home equipment. The system is tested and analyzed under experimental conditions. The test results show that the system can control home facilities through voice commands combined with real‐time environmental information while confirming family members.

Are YouTube and Facebook Canceling Classical Musicians? The Harmful Effects of Automated Copyright Enforcement on Social Media Platforms

During the height of the COVID-19 pandemic, classical musicians had to find virtual alternatives for reaching their audiences after canceling recitals and concert seasons. Social media platforms seemingly provided the perfect solution by providing the ability to broadcast live music and upload prerecorded performances for audiences to view, leading to income and a sustained social media presence; however, the use of hash matching and classification machine learning to monitor uploaded content for copyright infringement complicates the issue when these methods are unable to distinguish between copyrighted performances and original recordings of works in the public domain. This article explains the mechanics and applications of hashing and classification methods in YouTube and Facebook's automated copyright enforcement systems and suggests incorporating crowdsourcing, voice recognition technology, metadata analysis, and human moderator intervention as improvements which may mitigate the negative impacts these programs may have on classical musicians.

"Mojiko", A Savior Web App, Designed and Developed by a Public Media Company to Convert Audio &amp; Video to Text, Specifically Using Its AI Voice Recognition Technology

テレビラジオ業界では取材した素材の「文字起こし」業務が長年の課題である．とても大切な業務である一方，クリエイティブな作業とは言えず地道なもので，膨大な時間が費やされるこの「文字起こし」を若手スタッフが嫌がり，退職してしまうケースも数多くあった．文字起こしはまさに「地獄」である．その打開策として開発した「もじこ」は，音声認識AIを活用，自動でテキスト化された文字列を見ながら，音声・動画ファイルを聴きながら，実時間をかけずに「即座に」修正・編集が可能である．GoogleやMicrosoft，日本最大手アドバンストメディア社等の複数社のエンジンを搭載し，世界125を超える言語に対応，認識率の高いエンジンを自由に選ぶことができる．またPCにインストールが不要なウェブアプリとして開発したため，IDがあれば誰でもネット環境下で利用可能で，随時ユーザの意見を取り入れ，改善アップデートが即座にできる利便性が強みである．

APP Medical Diagnostic Check-up Consultation System Based on Speech Recognition

Background:Medical test orders can display the physiological functions of patients by using medical means. The medical staff determines the patient's condition through medical test orders and completes the treatment. However, for most patients and their families, there are so many terminologies in the medical test list and they are inconvenient to understand and query, which would affect the patients’ cognition and treatment effect. Therefore, it is especially necessary to develop a consulting system that can provide related analysis after getting medical test data.Objective :This paper starts with information acquisition and speech recognition. It proposes a natural scene information acquisition and analysis model based on deep learning, focusing on improving the recognition rate of routine test list and achieving targeted smart search to allow users to get more accurate personalized health advice.Methods :Based on medical characteristics, considering the needs of patients, this paper constructs an APP-based conventional medical test consultation system, using artificial intelligence and voice recognition technology to collect user input; analyzing user needs with the help of conventional medical information knowledge database.Results:This model combines speech recognition and data mining methods to obtain routine test list data and is suitable for accurate analysis of problems in routine check-up procedure. The app provides effective explanations and guidance for the treatment and rehabilitation of patients.Conclusion:It organically links the Internet with personalized medicine, which can effectively improve the popularity of medical knowledge and provide a reference for the application of medical services on the Internet. Meanwhile, this app can contribute to the improvement of medical standards and provide new models for modern medical management.

Active-beacon-based driver sound separation system for autonomous vehicle applications

Voice recognition technology can almost accurately recognize a user’s voice in the absence of background noise or when the noise levels are extremely low. However, voice recognition in the presence of background noise with various voice signals is complicated. The problem in the current voice separation scheme is that though voice separation is possible from mixed voice signals, a permutation problem occurs that renders it difficult to identify the desired signal among the separated signals. In this paper, we propose a driver voice separation method for autonomous vehicles. To solve the permutation problem, active-beacon-based driver sound separation (ABDSS) utilizing active sound is used to distinguish the driver’s sound. After recording the voice work, simulation was performed. In the simulation, the proposed method succeeded in separating and distinguishing the original voice signals from the mixed voice signals. In addition, the coherence, kurtosis, and skewness calculation were used to verify that the separated signals were correctly identified in the simulation. Therefore, the proposed method is simpler in terms of hardware configuration than the existing methods and it is suitable for in-vehicle voice separation systems as well.

Development of Smart Librarian with the Virtual Assistant (PRIMO)

In modern life, with the ability to perform tasks, the virtual assistant (VA) can make our lives easier and smart. The virtual assistant can perform as a librarian, very smartly, and effectively. We build our VA with Raspberry Pi and Alexa Voice Service. As a result, few discussions that occur in library environments such as find books, short review books, university notice are accurately performed. The common way of communication used by people in day to day life is through speech. If the assistant system can be heard to the customer for the handle of the day to day affairs, then grant the right reply, it will be much simple for customers to transmit with their assistant system, and the assistant will be much better “Smart” as a personal assistant. We heard a very old story “Ali Baba and the Forty Thieves”, where the mouth of a treasure cave secured by magic. It unrolls on the words "unroll sesame" and seals itself on the words "near sesame". The magic is a VA in the modern world. The VA system built on artificial intelligence (AI), machine learning, natural language processing, and voice recognition technology.