Re: who knows distributed recognition?

On Jul 21, 5:55 pm, Dirk Schnelle <dirk.schne...@xxxxxxxx> wrote:
Hi,

I am interested in experimenting distributed recognition. As far as I
understood it means that recording and feature extraction are performed
on a client and sent to a server to do the actual recognition.
Have you heard about any free API doing it? Is there any standard for
this kind of systems? Is it be part of a VoIP standard? Any known
experiment with HTK or Sphinx? Any pointer would be greatly appreciated!

You could check the paper from Alan Delaney:
A low power, fixed point feature extraction for a distributed speech
recognition system

This one is based on sphinx2. But I think that there are aloso newer
experiments based on sphinx3 and even sphinx4.

I don't think that this is the future of speech recognition. Newer
technologies or protocols, like MRCP, rely on audio streaming.

As far as I know, DSR is not being used to transfer VoIP. This would mean
that the speech signal must be reconstructed from the computed features.

hth
/dirk

Hi Dirk,

Thanks a lot for your answer. What do you think are the drawbacks of
distributed recognition? I thought it allowed performing speech
recognition on a speech signal which has not been compressed (features
are extracted from the raw signal on the client), and with a low
bandwidth (feature stream is much smaller than audio stream).

Thanks again for your help

.

Relevant Pages

  • Re: who knows distributed recognition?
    ... on a client and sent to a server to do the actual recognition. ... experiment with HTK or Sphinx? ... fixed point feature extraction for a distributed speech ... I don't think that this is the future of speech recognition. ...
    (comp.speech.research)
  • CiceroUlwndframe - Will not let me shut down machine
    ... "CiceroUlWndFrame" error upon Windows ... This error is caused by the "Speech and Handwriting ... Recognition" feature of MS Office. ...
    (microsoft.public.windowsxp.general)
  • Re: Face features extration
    ... If you need feature extraction (in the sense of pattern ... recognition), you may try PCA,LDA,ICA or LFA. ... Otherwise, if you mean "facial feature localization", I do not know you ...
    (sci.image.processing)
  • Re: Speech Recognition Toolkits - Requirements
    ... Despite the variety of ASR and SAPI systems around, ... mess up the operation of speech syntheses, so the ASR must probably have ... As you can see, integration of recognition and synthesis, while being ... These tools help the developer build a language-specific ASR Engine around a set of mathematical models, providing required APIs. ...
    (comp.speech.users)
  • Re: NewLine bug of Windows Speech Recognition revisited
    ... especially where spelling is concerned and that is with any app! ... "Queen's English" (going on how long it has taken you to learn speech ... In reading into certain posts, most people in here including myself think ... so long to learn how to use speech recognition and more importantly SPELLING ...
    (microsoft.public.windows.vista.general)