Chris@0: %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Chris@0: % Name: test_convert_audio_to_pitchSTMSP.m
Chris@0: % Date of Revision: 2011-03
Chris@0: % Programmer: Meinard Mueller, Sebastian Ewert
Chris@0: %
Chris@0: % Description: 
Chris@0: % * Computes pitch subband decomposition of WAV file
Chris@0: %   (default: MIDI pitches 21 to 108) 
Chris@0: % * each pitch subband contains short time mean-square power (STMSP) 
Chris@0: % * Features are computed in a batch modus
Chris@0: % * Features are stored in folder 'data_feature/'
Chris@0: %
Chris@0: % Reference: 
Chris@0: % Details on the feature computation can be found in the following book:
Chris@0: %
Chris@0: % Meinard Mueller: Information Retrieval for Music and Motion,
Chris@0: %                  Springer 2007
Chris@0: %
Chris@0: % License:
Chris@0: %     This file is part of 'Chroma Toolbox'.
Chris@0: % 
Chris@0: %     'Chroma Toolbox' is free software: you can redistribute it and/or modify
Chris@0: %     it under the terms of the GNU General Public License as published by
Chris@0: %     the Free Software Foundation, either version 2 of the License, or
Chris@0: %     (at your option) any later version.
Chris@0: % 
Chris@0: %     'Chroma Toolbox' is distributed in the hope that it will be useful,
Chris@0: %     but WITHOUT ANY WARRANTY; without even the implied warranty of
Chris@0: %     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
Chris@0: %     GNU General Public License for more details.
Chris@0: % 
Chris@0: %     You should have received a copy of the GNU General Public License
Chris@0: %     along with 'Chroma Toolbox'. If not, see <http://www.gnu.org/licenses/>.
Chris@0: % 
Chris@0: %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Chris@0: clear;
Chris@0: close all hidden;
Chris@0: 
Chris@0: dirFileNames = {
Chris@0:     'data_WAV/','Bach_BWV988-Aria-Measures1-4_Meinard_fast.wav';
Chris@0:     'data_WAV/','Burgmueller_Op100-02-FirstPart_Meinard_SE.wav';
Chris@0:     'data_WAV/','Systematic_Cadence-C-Major_Meinard_portato.wav';
Chris@0:     'data_WAV/','Systematic_Cadence-C-Major_Meinard_staccato.wav';
Chris@0:     'data_WAV/','Systematic_Scale-C-Major_Meinard_fast.wav';
Chris@0:     'data_WAV/','Systematic_Scale-C-Major_Meinard_middle.wav';
Chris@0:     'data_WAV/','Systematic_Chord-C-Major_Eight-Instruments.wav';
Chris@0:     };
Chris@0: 
Chris@0: for n=1:size(dirFileNames,1)
Chris@0:     clear parameter;
Chris@0:     parameter.message = 1;
Chris@0:     
Chris@0:     %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Chris@0:     % Convert WAV to expected audio format (mono, 22050 Hz)
Chris@0:     %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Chris@0:     
Chris@0:     [f_audio,sideinfo] = wav_to_audio('', dirFileNames{n,1}, dirFileNames{n,2},parameter);
Chris@0:         
Chris@0:     %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Chris@0:     % Estimation of the global tuning of the recording and selection of
Chris@0:     % an appropriate filterbank for use in the next step
Chris@0:     %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Chris@0:     clear parameter
Chris@0:     shiftFB = estimateTuning(f_audio);
Chris@0:     fprintf('Using filterbank number: %d\n',shiftFB);
Chris@0: 
Chris@0:     %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Chris@0:     % Compute pitch features
Chris@0:     % 
Chris@0:     % Input: audio file of format: mono, 22050 Hz
Chris@0:     %
Chris@0:     % Output: sequence of pitch vectors 
Chris@0:     %         (specified by N x 120 matrix f_pitch)
Chris@0:     %         Only subband for MIDI pitches 21 to 108 are computed, the
Chris@0:     %         other subbands are set to zero.
Chris@0:     %
Chris@0:     % Parameter: parameter.win_len specifies window length (in samples)
Chris@0:     %            with window overlap of half size  
Chris@0:     %            Example: audio sampling rate: 22050 Hz
Chris@0:     %                     parameter.win_len = 4410
Chris@0:     %                     Resulting feature rate: 10 Hz
Chris@0:     %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Chris@0: 
Chris@0:     clear parameter
Chris@0:     parameter.winLenSTMSP = 4410;
Chris@0:     parameter.fs = sideinfo.wav.fs;
Chris@0:     parameter.save = 1;
Chris@0:     parameter.saveDir = 'data_feature/';
Chris@0:     parameter.saveFilename = dirFileNames{n,2}(1:end-4);
Chris@0:     parameter.shiftFB = shiftFB;
Chris@0:     parameter.saveAsTuned = 1;
Chris@0:     [f_pitch,sideinfo] = audio_to_pitch_via_FB(f_audio,parameter,sideinfo);
Chris@0:     
Chris@0:     %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Chris@0:     % Visualization of pitch decomposition (f_pitch)
Chris@0:     %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Chris@0:     
Chris@0:     parameter.usePitchNameLabels = 1;
Chris@0:     parameter.title = 'Logarithmic compression of amplitude';
Chris@0:     parameter.featureRate = sideinfo.pitch.featureRate;
Chris@0:     parameter.xlabel = 'Time [Seconds]';
Chris@0:     parameter.ylabel = 'Pitch';
Chris@0:     visualizePitch(log(5*f_pitch+1),parameter);
Chris@0: end