[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.

               Laszlo Toth
        Hungarian Academy of Sciences         *
  Research Group on Artificial Intelligence   *   "Failure only begins
     e-mail: tothl@xxxxxxxxxxxxxxx            *    when you stop trying"
     http://www.inf.u-szeged.hu/~tothl        *