[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: MFCC method
On Thu, 8 Jan 2009, Arturo Camacho wrote:
> I wonder if it would not be an even better idea to use the Greenwood
> function (see entry in Wikipedia), which was explicitly created with
> that purpose.
I'm pretty sure I've seen papers comparing various frequency warping
scales in MFCC, but none of them made a significant difference compared to
the mel scale (at least, with respect to speech recognition performance).
I can't name an exact reference, though.
Hungarian Academy of Sciences *
Research Group on Artificial Intelligence * "Failure only begins
e-mail: tothl@xxxxxxxxxxxxxxx * when you stop trying"