speech extraction

On 05/09/2011 06:14 PM, maury wrote:
> On May 9, 10:31 am, "vishnuj17" <vishnuj17@n_o_s_p_a_m.gmail.com>
> wrote:
>>> On 05/08/2011 05:12 PM, vishnuj17 wrote:
>>>> Hi.. I was trying to extract speech data from raw data with background
>>>> traffic. i tried wiener filter, but was not so good.
>>>> Could you share with me your suggestions that will help me to extract
>>>> speech only from background noise
>>
>>> If by "speech" you mean the voice signal, then you might want to
>>> search for "VAD" ("voice activity detection") and "spectral
>>> subtraction."
>>> --
>>> Randy Yates                      % "So now it's getting late,
>>> Digital Signal Labs              %    and those who hesitate
>>> mailto://ya...@ieee.org          %    got no one..."
>>> http://www.digitalsignallabs.com% 'Waterfall', *Face The Music*, ELO
>>
>> also since the signal band and noise band are overlapped, ordinary spectral
>> subtraction will damage the signal also.
> 
> Not necessarily true. It depends on the SNR. Do a google search on
> _spectral subtraction speech enhancement_.  Also, if you don't get the
> parameters correct, you will defeat your purpose and screw up the
> signal. For a _basic_ discussion of the parameters and how to set them
> for a basic spectral subtraction noise reduction system, look up the
> comp.dsp 2004 conference and download a presentation on noise
> reduction techniques.

A good introduction can be found in

Peter Vary & Rainer Martin, "Digital Speech Transmission -- Enhancement,
Coding & Error Concealment", Wiley 2006

in Chapter 11. Spectral subtraction and Wiener filtering is explained
with many different solutions for estimating either the noise (by means
of minimum statistics for estimating non-stationary noise not requiring
VAD) or the speech psds or the respective SNRs, required in the algorithms.

You should however note that with a single microphone, you will be very
limited and you can hope to increase listening comfort. The increase in
speech intelligibility will be limited. Better results can be expected
if you can use two or more microphones. The above-mentioned book also
includes examples for two or multi-microphone setups.

You can also take a look at the homepage of one of the authors:
http://www.ind.rwth-aachen.de/en/research/speech-and-audio-processing/noise-reduction/
which includes also examples. Further information is found on
http://www.ruhr-uni-bochum.de/ika/

Regards,
Laurent

>On 05/09/2011 06:14 PM, maury wrote:
>> On May 9, 10:31 am, "vishnuj17" <vishnuj17@n_o_s_p_a_m.gmail.com>
>> wrote:
>>>> On 05/08/2011 05:12 PM, vishnuj17 wrote:
>>>>> Hi.. I was trying to extract speech data from raw data with
background
>>>>> traffic. i tried wiener filter, but was not so good.
>>>>> Could you share with me your suggestions that will help me to
extract
>>>>> speech only from background noise
>>>
>>>> If by "speech" you mean the voice signal, then you might want to
>>>> search for "VAD" ("voice activity detection") and "spectral
>>>> subtraction."
>>>> --
>>>> Randy Yates                      % "So now it's getting late,
>>>> Digital Signal Labs              %    and those who hesitate
>>>> mailto://ya...@ieee.org          %    got no one..."
>>>> http://www.digitalsignallabs.com% 'Waterfall', *Face The Music*, ELO
>>>
>>> also since the signal band and noise band are overlapped, ordinary
spectral
>>> subtraction will damage the signal also.
>> 
>> Not necessarily true. It depends on the SNR. Do a google search on
>> _spectral subtraction speech enhancement_.  Also, if you don't get the
>> parameters correct, you will defeat your purpose and screw up the
>> signal. For a _basic_ discussion of the parameters and how to set them
>> for a basic spectral subtraction noise reduction system, look up the
>> comp.dsp 2004 conference and download a presentation on noise
>> reduction techniques.
>
>A good introduction can be found in
>
>Peter Vary & Rainer Martin, "Digital Speech Transmission -- Enhancement,
>Coding & Error Concealment", Wiley 2006
>
>in Chapter 11. Spectral subtraction and Wiener filtering is explained
>with many different solutions for estimating either the noise (by means
>of minimum statistics for estimating non-stationary noise not requiring
>VAD) or the speech psds or the respective SNRs, required in the
algorithms.
>
>You should however note that with a single microphone, you will be very
>limited and you can hope to increase listening comfort. The increase in
>speech intelligibility will be limited. Better results can be expected
>if you can use two or more microphones. The above-mentioned book also
>includes examples for two or multi-microphone setups.
>
>You can also take a look at the homepage of one of the authors:
>http://www.ind.rwth-aachen.de/en/research/speech-and-audio-processing/noise-reduction/
>which includes also examples. Further information is found on
>http://www.ruhr-uni-bochum.de/ika/
>
>Regards,
>Laurent
>
I am now using matlab to simulate the algorithm because of the easiness and
i am using ordinary sound card. that why i used a simple mic. how can be
the spatial diff be useful if i use more than one.

On May 8, 6:26&#4294967295;pm, Richard Owlett <rowl...@pcnetinc.com> wrote:
> Randy Yates wrote:
> > On 05/08/2011 05:12 PM, vishnuj17 wrote:
> >> Hi.. I was trying to extract speech data from raw data with background
> >> traffic. i tried wiener filter, but was not so good.
> >> Could you share with me your suggestions that will help me to extract
> >> speech only from background noise
>
> > If by "speech" you mean the voice signal, then you might want to
> > search for "VAD" ("voice activity detection") and "spectral
> > subtraction."
>
> And if he was trying to extract "intelligence" ? ???
*to the author of the above comment*
If everyone already knew everything about everything, there would be
no need for forums like this and people like you, (with no life) would
have nowhere to hang out and make stupid unhelpful comments... then
where would you be?
++++And if he was trying to extract "intelligence" ? ???+++++
If you know all the answers to a point where everyone is inferior to
you, then put it to use and go build something useful!! jackass!