Speech to text conversion pronunciation problem.

Question

0.00/5 (No votes)

See more:

I have created application to convert speech to text.
I have use

C#

using System.Speech.Recognition;
using System.Speech.Synthesis;

I am converting English speech to text and have use en-US to create speech engine.

C#

private SpeechRecognitionEngine _speechRecognitionEngine = new SpeechRecognitionEngine("en-US");

I have use .net dictation grammar.

C#

#region Load .Net defatult grammer.
// Load Dictation Grammer 
DictationGrammar dictationGrammer = new DictationGrammar();
_speechRecognitionEngine.LoadGrammar(dictationGrammer);
#endregion

To explain in short what I did except that using .net dictation grammar for wider scope as mention above.
I have use same code as following code project articular.
C# Speech to Text[^]
Problem domain
I am staying in India.
People do not have us en pronoun cation.
When i am converting form speech to text I am getting irrelevant conversion.
Like when i say "good day it" convert some thing "go day it".
can you guide me?
You help will be appreciated.

Posted 18-May-13 23:53pm

Amey K Bhatkar

Updated 19-May-13 4:35am

Kenneth Haugland

v4

Add a Solution

Comments

Richard MacCutchan 19-May-13 7:24am

The system can only convert what it "hears", and you may find that different accents produce different reults. While nearly everyone in India speaks excellent English, their accents are often difficult to understand.

Amey K Bhatkar 19-May-13 10:26am

Agree but what is need to do now to get exact speech to text.
And I have told one of my colleague having US accent of speaking.
Speech to text work fine with small world like good morning.
But it fail for the long sentence.
There are third party s/w that work fine for the long sentence.
So they are using some thing more that I am missing.

2 solutions

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)

Ron Beyer · Accepted Answer · 2013-05-19T04:34:00

You have to have the user go through the speech to text training. By default Windows is trained to the en-US common voice, if you want to use it in another accent, you will have to run through the training wizard 5 or 6 times for better STT results.

http://windows.microsoft.com/en-us/windows7/set-up-speech-recognition[^]

Dave Kreskowiak · Accepted Answer · 2013-05-19T05:17:00

Solution 2

Like has already been said, each user must go through this training wizard multiple times, per machine.

But what hasn't been said is that you will never get perfect results. Dragon is just about the best STT engine there is and Mr even it can achieve 100% accuracy.

Posted 19-May-13 5:17am

Dave Kreskowiak