What happens to the text from Speech which doesn't recognize as command, MS Speech SDK 11

Question

0.00/5 (No votes)

See more:

Hi All,

I am working on some speech enabled application using MS Speech SDK v11. I want to recognize the commands I specify in my SRGS document, at the same time, if some speak something else, I want that to be converted to simple text and be stored. I tried using Dictation mode, so that I can just continue in Dictation and get the text. Then using custom built SRGS parser, determine the commands. If the text is not predefined command, just treat it as simple text. Now problem is the AppendDictation is not working due to "Cannot find grammar referenced by this grammar." and I referred this http://stackoverflow.com/questions/9347346/appenddictation-on-microsoft-speech-platform-11-server

I changed from Microsoft.Speech to System.Speech and interestingly found that Microsoft.Speech at least recognize the commands I specify but System.Speech is doing nothing. I am confused what to do.

I repeat, I have simple requirement, recognize the commands I specify and if not just translate those in Text form. If this is not possible then how can I make work Speech API for dictation mode only.

Also just a quick question, as previously, we had to train the computer to understand our speech and create profile, does current speech engine also must be trained? Or it fine tunes itself as we speak frequently?

Thank you in advance!

Posted 10-Jul-14 8:34am

mymedia

Add a Solution

1 solution

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Sergey Alexandrovich Kryukov · Answer 1 · 2014-07-10T10:47:00

Right. The quality of the recognition engine which you can download from Microsoft is not good enough for Dictation. If your grammar is reasonably small, it works reasonably well, but even then you might need to use better pronunciation. :-) Actually, some say there are much better commercial engines, including the one from the company which licensed to Microsoft the present-day engine for Windows. I don't know what else to suggest, probably wait until technology improves. :-)

—SA