Open AccessSpeech recognition model for solution of website element management tasks
Author(s) -
Yulia Lytvyn,
Oksana Strokan
Publication year - 2018
Publication title -
ukrainian journal of educational studies and information technology
Language(s) - English
Resource type - Journals
ISSN - 2521-1234
DOI - 10.32919/uesit.2018.02.06
Subject(s) - computer science , usability , javascript , speech technology , microphone , task (project management) , process (computing) , control (management) , world wide web , speech analytics , human–computer interaction , speech synthesis , multimedia , speech recognition , speech corpus , artificial intelligence , engineering , telecommunications , systems engineering , sound pressure , operating system
The article deals with the method of speech recognition, namely, the possibility of using this technology for the language control of website elements. Due to the widespread introduction of such technologies into human lives, the task is to create a voice application that would improve the usability. The feature of the proposed model is the implementation of speech recognition not in the service, as it happens in most cases, but in the device itself, using only a microphone. In the existing design users can easily add any commands. Language recognition is implemented on the website page using the JavaScript programming language. The script work is based on the use of the SpeechRecognition Web Speech APIs and the SpeechGrammarList API for Web Speech. The current direction of the use of speech in the process of interaction between the technical system and the user is the application of such technology for creating comfortable living conditions for people who have a violation of the musculoskeletal system and who have lost the opportunity to use traditional means and methods of dialogue with the system. It analyzed the basic principles of the website and the ability to control it using voice control. To operate the proposed speech recognition model, two interfaces are used to solve the problem of managing elements of a website: SpeechRecognition Web Speech API and SpeechGrammarList API Web Speech. In order to manage the elements of the website, a model is proposed, the implementation of which is possible through the use of a microphone on the user's desktop only. The feature of the proposed model is that it is easy to add any commands to an already existing structure. Such application provides a great perspective for building new web interfaces in combination with artificial intelligence.