Speech Recognizer Interface Usage
The speech recognition unit will recognize numbers from 0 to 9, and the words 'YES' and 'NO.'
The user will say, in English, an account number (of at least 16 numbers) and the interface will pass the number to the webserver which will interpret and repeat the account number to the user using text to speech (not simply replaying the users sound file), the number back to the user. The interface will then ask "Is this correct?", and the user will state 'YES' or 'NO.' If the user says 'NO,' the interface will wait for the user to repeat the number and resend to the server.
Number input should be terminated by silence, not by a keypress or mouse.
Speech recognizer should have at least 75% accuracy for the numbers 0 to 9 and yes and no.
Must run on Chrome and Firefox.
Conversion software server will use WebSockets or WebRTC.
Server must run on Ubuntu Linux platform.
Server can be implemented in PHP, Perl, Python, Ruby or C.
DO NOT USE Node.js
The speech to text and text to speech conversion must be done by open source software on the server. NO third party web services allowed.
24 freelancers are bidding on average $590 for this job
i can make Speech to text, text to speech web client and server. I have 8+ years of experience in php. I am online. I am ready to start. Please reply so that we can discuss further.
Hello I am ML Expert with Tensorflow, CNTK, FasterCNN. I read your job and understood. I can start this job now and work full time. I will wait your right choice. Thank you.
I DO NOT OUTSOURCE I have been a freelancer for the past 8 years, I believe that my experience and skill in this background will prove to be of great help to you. Contact me to discuss more on the details