Re: evaluation of speech enhancement algorithm. How?

Hi

Thanks for the link :o)

Maybe I should have started out with a brief description of my algorithm.
First of all...I have 2 wav-files.
One file is the clean speech signal (s[k]) and the other file is pink noise
(n[k]). These two files are added together after
having scaled the pink noise signal according to a pre-defined SNR. The
noisy speech signal x[k] is fed to my algorithm
16 samples at a time. The 16 samples are put in a 256 samples long frame.
Based on the contents of the frame
I calculate the power spectrum X of the frame and subtract the average noise
power spectrum N and obtain the power spectrum P. I have found this
average noise power spectrum N by averaging lots of power spectras which I
know only contain noise. I then convert P to a modelbased spectrum
(LPC-analysis).
I then do some filtering and convert the manipulated power spectrum Pm to
LPC-coefficients. Thats the frame processing.

The block processing takes in those 16 samples I mentioned in the beginning
and send them through a whitening filter. The whitened signal
is sent through a filter that models the vocal tract. The filter that models
the vocal tract gets its coefficients from the LPC-analysis performed
on the manipulated power spectrum Pm. The output from the vocal tract filter
is the estimated speech.

I hope this clarifies things a little bit :o)

Where can I download a speech recognizer that will accept a wav-file (the
estimated speech) as input?

Thanks in advance..


.

Relevant Pages

  • Re: Masking a speech signal
    ... I am trying to selectively mask a speech signal with white ... I mean i would like the noise ... Design the filter so that it will track the envelope ... of the speech waveform, and compare its output to a threshold. ...
    (comp.dsp)
  • Re: Masking a speech signal
    ... I am trying to selectively mask a speech signal with white ... Design the filter so that it will track the envelope ... of the speech waveform, and compare its output to a threshold. ... can reliably discriminate between noise and signal + noise. ...
    (comp.dsp)
  • Re: Masking a speech signal
    ... I am trying to selectively mask a speech signal with white ... Design the filter so that it will track the envelope ... of the speech waveform, and compare its output to a threshold. ... can reliably discriminate between noise and signal + noise. ...
    (comp.dsp)
  • Re: Clean speech wav files
    ... characterize your algorithm, you might try colored noises, as well as ... supply harmonics, bumblebee noise, road noise, etc. ... Yes..i'm going to try out speech recorded at the cafeteria and in a car ... can filter out any portion that may contain speech, else,their energy may ...
    (comp.dsp)
  • Re: Question about inflation theory
    ... receiver to receiver i.e. for the internal receiver noise (that's the ... we are agreed that method used removes the uncorrelated noise ... there could be a tiny correlated bias in the auto power ... To calculate a power spectrum WMAP does a cross power analysis of one ...
    (sci.astro)