Speech Recognition Engines

Flat
How can we get the phoneme in speech recognition
User: kmaclean
Date: 6/18/2008 11:13 am
Views: 9565
Rating: 12

rks_mfs  asks:

Hi,

I am trying to get Sphinx to work with Indian languages and thinking of working with phone set for one language at a time.

What is the best approach to do this in Sphinx. Can I directly work with phoneme decoder so that I do not have to get into Vocabulary and word dictionary.

Does Sphinx do phoneme only output and is the recognition real time.

for instance if I say "Hello" how can i get a phoneme which recognize 'h' first then 'e' then 'l' then 'l' then 'o' each independently?


Thanks.

--- (Edited on 6/18/2008 12:13 pm [GMT-0400] by kmaclean) ---

Re: How can we get the phoneme in speech recognition
User: kmaclean
Date: 6/18/2008 11:28 am
Views: 111
Rating: 15

Hi rks_mfs,

>I am trying to get Sphinx to work with Indian sub-languages and thinking of

>working with phone set for one language at a time.

Do you mean you want Sphinx to recognize speech from more than one Indian language at the same time? Why? what is the application you are thinking of?

>thinking of working with phone set for one language at a time.

Do you mean that you want to have a separate phone set for each Indian sub-language?  

>for instance if I say "Hello" how can i get a phoneme which recognize 'h'

>first then 'e' then 'l' then 'l' then 'o' each independently?

Why would you want to do this?  What are you trying to do? 

Strictly speaking, speech recognition works with phones rather than phonemes, so that it only distinguishes between distinct units of sound.  If in your target language, a letter matches directly to a sound, then you should be able to use speech recognition to distinguish the letters.  This is *not* the case in English.

Hope that helps, 

Ken 

 

--- (Edited on 6/18/2008 12:28 pm [GMT-0400] by kmaclean) ---

Re: How can we get the phoneme in speech recognition
User: ken
Date: 6/19/2008 3:48 am
Views: 166
Rating: 14
Hello Ken,
We are very thankfull for your  guidence.
I am working with an Indian language "Hindi" in which a letter matches directly with a sound.
For this , we will have to create an acoustic model and dictonary in which mapping between alphabet and phoneme is defined.
For grapheme-based acoustic modeling, where can I find the steps necessary to build the dictionary by treating each character as a phone. What are the requirements to follow this track.
With Regards
rks_mfs

--- (Edited on 6/19/2008 3:48 am [GMT-0500] by Visitor) ---

Re: How can we get the phoneme in speech recognition
User: kmaclean
Date: 6/19/2008 7:13 am
Views: 115
Rating: 14

Hi rks_mfs,

>For grapheme-based acoustic modeling, where can I find the steps necessary

>to build the dictionary by treating each character as a phone.

Use Google. 

This first article speaks directly to your question:

These articles talk about using English acoustic models to bootstrap phone models for a new language:

Ken

--- (Edited on 6/19/2008 8:13 am [GMT-0400] by kmaclean) ---

Re: How can we get the phoneme in speech recognition
User: nsh
Date: 6/19/2008 3:25 pm
Views: 184
Rating: 14

Btw, Hindi models for sphinx were recently released:

  http://sourceforge.net/projects/hindiasr/

--- (Edited on 6/19/2008 3:25 pm [GMT-0500] by nsh) ---

Re: How can we get the phoneme in speech recognition
User: ken
Date: 6/25/2008 12:02 am
Views: 130
Rating: 10
Hello Ken,
We are very thankfull for your  guidence.
I want to test the sphinx-3 decoder in windows using a wave file. But I do not have any application which could perform this task.
Since I am new user of sphinx so I do not have much idea about sphinx-3.
So can you please guide me what are the steps we will have to follow to do this work.
Thanks 

--- (Edited on 6/25/2008 12:02 am [GMT-0500] by Visitor) ---

Re: How can we get the phoneme in speech recognition
User: kmaclean
Date: 6/25/2008 9:13 am
Views: 319
Rating: 11

Hi,

>So can you please guide me what are the steps we will have to follow to do

>this work.

See the Sphinx Manual: Hieroglyphs

Ken

--- (Edited on 6/25/2008 10:13 am [GMT-0400] by kmaclean) ---

Re: How can we get the phoneme in speech recognition
User: kmaclean
Date: 7/21/2008 1:45 pm
Views: 5318
Rating: 10

You might also try the CMU Robust Group Tutorial (dated Aug 2007).

 

--- (Edited on 7/21/2008 2:45 pm [GMT-0400] by kmaclean) ---

PreviousNext