Speech recognition using Labview 7.0 on winXP??

[sattu]

Hi all,I am new to Labview.
I want to recognize my speech(voice),please give me answer of following question:
1.basic criterion by which I can distinguished different speeches(voices) and what is common in all voices for same character(ex. in "a","e","i","o","u")???
2.How to perform above task??(I mean rough Ideas like filtering,windowing,which plot frequency or magnitude or anything else,And Matching this means how can I say this is my voice not any one else???
Please help me I am really waiting for your reply so please reply me if you have any Ideas??

[Bob_Y.]

I am a bit unsure of what you are trying to accomplish. Are you trying to recognize ANY voice (someone said "hello") or are you trying to differentiate between voices (Mary is the person talking)? If it is the first, I think you would have better luck with calling a commercial package.

If it is the differentiation, you can have a message for them to say and then compare the waveforms that are spoken. I think you would want to compare the envelopes of the waveforms in some way. Maybe using spectral measurements to determine the main frequency components of the entered waveform.

[LesHammer]

> Are you trying to recognize ANY voice (someone said "hello")
> I think you would have better luck with calling a commercial package.

Especially when it comes to accents - the extreme being when "hello" is pronounced "howdy" 🙂

Les

[JuanCarlos]

Sattu,

In windows platforms you can use Microsoft's Speech Software Development Kit (SDK). This is basically a library to convert text to speech and speech recognition. Creating your ouw speech recognition ruotines in LabVIEW is possible, however you will need advanced DSP knowledge, and a lot of time.

You can find more info on the Speech SDK at http://www.microsoft.com/speech/download/sdk51/

I hope this helps.

Regards,

Juan Carlos
N.I.