SPEECH ENABLED OPERATING SYSTEM

SPEECH ENABLED OPERATING SYSTEM

Mr  ARUL E1 ,VISHNU PRASANTH B S2, SUGANTH S3 , MITHUNRAJ P4 , KATHIRAVAN M5

Department of Information Technology,

Coimbatore Institute of Technology,

Coimbatore, Tamil Nadu, India.

             { 1 arul.e@cit.edu.in

271762107058@cit.edu.in,

             371762107051@cit.edu.in,

            471762207204@cit.edu.in,

571762107021@cit.edu.in }

ABSTRACT

The concept of the work is to create a speech interface while controlling computers using OS to manage computer operations through speech. It is more than a mere corridor is giving a smooth entry into a computer but at the same time we have made what seems to be complex operation very easy. It has been implemented on the Linux platform and uses Speech Recognition libraries with Google Speech API to convert typed direct spoken word commands to the computer fully optimized with pyttsx3 python for feedback voice output to the user. The features that are supported by this interface include typing, opening, closing, creating, deleting, renaming files, searching the web, starting other applications, etc. First it includes converting the input speech into text, the second step is parsing this text to match with the request to the coded Python codes to perform the desired action. This modularity has the Command Module for acquiring a module capturing voice, through which inputs matched will be action, the Action Module for action, and the Feedback Module through voice response confirmation. The Bash script operates with systemd- to start the interface at system boot in order to run this code under the Python virtual environment with the name myenv. This type of interface is most suitable for the disabled as it enhances convenience and flexibility in making assimilation to smart OS environments.