Re: evaluation of speech enhancement algorithm. How?
- From: "dbell" <dbell@xxxxxxxxxx>
- Date: 28 Sep 2005 19:26:11 -0700
So you are trying to make the voice sound like you had not added the
pink noise in the first place? Can you give some idea what your
relative speech/noise levels are?
Where did the whitening filter come from?
When you turn the noise level down and analyze/synthesize the waveforms
do the original (clean) signal and reconstructed signal look similar on
a point-by-point basis? If not, then subtracting waveforms and looking
at errors is not the way to evaluate the 'quality'.
Do some searching on "LPC analysis in noise".
Dirk
.
- Follow-Ups:
- Re: evaluation of speech enhancement algorithm. How?
- From: Lars Hansen
- Re: evaluation of speech enhancement algorithm. How?
- References:
- Re: evaluation of speech enhancement algorithm. How?
- From: dbell
- Re: evaluation of speech enhancement algorithm. How?
- From: Lars Hansen
- Re: evaluation of speech enhancement algorithm. How?
- Prev by Date: Re: parallel FIR filters
- Next by Date: Re: fractional-sample delay filtering
- Previous by thread: Re: evaluation of speech enhancement algorithm. How?
- Next by thread: Re: evaluation of speech enhancement algorithm. How?
- Index(es):
Relevant Pages
|
|