Changeset fa713bd for src/spectral/filterbank_mel.h

Timestamp:

Nov 17, 2018, 3:15:07 AM (5 years ago)

Author:

Paul Brossier <piem@piem.org>

Branches:

feature/autosink, feature/cnn, feature/cnn_org, feature/constantq, feature/crepe, feature/crepe_org, feature/pitchshift, feature/pydocstrings, feature/timestretch, fix/ffmpeg5, master

Children:

04cd251

Parents:

2886984

Message:

[filterbank] add set_mel_coeffs

File:

• src/spectral/filterbank_mel.h (modified) (2 diffs)

src/spectral/filterbank_mel.h

@@ -58 +58 @@
   \param samplerate audio sampling rate
 
-  The filter coefficients are built according to Malcolm Slaney's Auditory
-  Toolbox, available online at the following address (see file mfcc.m):
+  The filter coefficients are built to match exactly Malcolm Slaney's Auditory
+  Toolbox implementation (see file mfcc.m). The number of filters should be 40.
 
+  References
+  ----------
+
+  Malcolm Slaney, *Auditory Toolbox Version 2, Technical Report #1998-010*
   https://engineering.purdue.edu/~malcolm/interval/1998-010/
 
@@ -67 +71 @@
     smpl_t samplerate);
 
+/** Mel filterbank initialization
+
+  \param fb filterbank object
+  \param samplerate audio sampling rate
+  \param fmin start frequency, in Hz
+  \param fmax end frequency, in Hz
+
+  The filterbank will be initialized with bands linearly spaced in the mel
+  scale, from `fmin` to `fmax`.
+
+  References
+  ----------
+
+  Malcolm Slaney, *Auditory Toolbox Version 2, Technical Report #1998-010*
+  https://engineering.purdue.edu/~malcolm/interval/1998-010/
+
+*/
+uint_t aubio_filterbank_set_mel_coeffs(aubio_filterbank_t * fb,
+    smpl_t samplerate, smpl_t freq_min, smpl_t freq_max);
+
+/** Mel filterbank initialization
+
+  \param fb filterbank object
+  \param samplerate audio sampling rate
+  \param fmin start frequency, in Hz
+  \param fmax end frequency, in Hz
+
+  The bank of filters will be initalized to to cover linearly spaced bands in
+  the Htk mel scale, from `fmin` to `fmax`.
+
+  References
+  ----------
+
+  Douglas O'Shaughnessy (1987). *Speech communication: human and machine*.
+  Addison-Wesley. p. 150. ISBN 978-0-201-16520-3.
+
+  HTK Speech Recognition Toolkit: http://htk.eng.cam.ac.uk/
+
+*/
+uint_t aubio_filterbank_set_mel_coeffs_htk(aubio_filterbank_t * fb,
+    smpl_t samplerate, smpl_t freq_min, smpl_t freq_max);
+
 #ifdef __cplusplus
 }