c@41: /* -*- c-basic-offset: 4 indent-tabs-mode: nil -*-  vi:set ts=8 sts=4 sw=4: */
c@41: 
c@41: /*
c@41:  * SegmenterPlugin.cpp
c@41:  *
c@41:  * Copyright 2008 Centre for Digital Music, Queen Mary, University of London.
c@41:  * All rights reserved.
c@41:  */
c@41: 
c@41: #include <iostream>
c@41: #include <sstream>
c@41: 
c@41: #include "SimilarityPlugin.h"
c@41: #include "dsp/mfcc/MFCC.h"
c@41: #include "dsp/rateconversion/Decimator.h"
c@41: 
c@41: using std::string;
c@41: using std::vector;
c@41: using std::cerr;
c@41: using std::endl;
c@41: using std::ostringstream;
c@41: 
c@41: SimilarityPlugin::SimilarityPlugin(float inputSampleRate) :
c@41:     Plugin(inputSampleRate),
c@41:     m_mfcc(0),
c@41:     m_decimator(0),
c@41:     m_K(20),
c@41:     m_blockSize(0),
c@41:     m_channels(0)
c@41: {
c@41: 	
c@41: }
c@41: 
c@41: SimilarityPlugin::~SimilarityPlugin()
c@41: {
c@41:     delete m_mfcc;
c@41:     delete m_decimator;
c@41: }
c@41: 
c@41: string
c@41: SimilarityPlugin::getIdentifier() const
c@41: {
c@41:     return "qm-similarity";
c@41: }
c@41: 
c@41: string
c@41: SimilarityPlugin::getName() const
c@41: {
c@41:     return "Similarity";
c@41: }
c@41: 
c@41: string
c@41: SimilarityPlugin::getDescription() const
c@41: {
c@41:     return "Return a distance metric for overall timbral similarity between the input audio channels";
c@41: }
c@41: 
c@41: string
c@41: SimilarityPlugin::getMaker() const
c@41: {
c@41:     return "Chris Cannam, Queen Mary, University of London";
c@41: }
c@41: 
c@41: int
c@41: SimilarityPlugin::getPluginVersion() const
c@41: {
c@41:     return 1;
c@41: }
c@41: 
c@41: string
c@41: SimilarityPlugin::getCopyright() const
c@41: {
c@41:     return "Copyright (c) 2008 - All Rights Reserved";
c@41: }
c@41: 
c@41: size_t
c@41: SimilarityPlugin::getMinChannelCount() const
c@41: {
c@41:     return 2;
c@41: }
c@41: 
c@41: size_t
c@41: SimilarityPlugin::getMaxChannelCount() const
c@41: {
c@41:     return 1024;
c@41: }
c@41: 
c@41: bool
c@41: SimilarityPlugin::initialise(size_t channels, size_t stepSize, size_t blockSize)
c@41: {
c@41:     if (channels < getMinChannelCount() ||
c@41: 	channels > getMaxChannelCount()) return false;
c@41: 
c@41:     if (stepSize != getPreferredStepSize()) {
c@41:         std::cerr << "SimilarityPlugin::initialise: supplied step size "
c@41:                   << stepSize << " differs from required step size "
c@41:                   << getPreferredStepSize() << std::endl;
c@41:         return false;
c@41:     }
c@41: 
c@41:     if (blockSize != getPreferredBlockSize()) {
c@41:         std::cerr << "SimilarityPlugin::initialise: supplied block size "
c@41:                   << blockSize << " differs from required block size "
c@41:                   << getPreferredBlockSize() << std::endl;
c@41:         return false;
c@41:     }        
c@41:     
c@41:     m_blockSize = blockSize;
c@41:     m_channels = channels;
c@41: 
c@41:     int decimationFactor = getDecimationFactor();
c@41:     if (decimationFactor > 1) {
c@41:         m_decimator = new Decimator(getPreferredBlockSize(), decimationFactor);
c@41:     }
c@41: 
c@41:     MFCCConfig config;
c@41:     config.FS = lrintf(m_inputSampleRate) / decimationFactor;
c@41:     config.fftsize = 2048;
c@41:     config.nceps = m_K - 1;
c@41:     config.want_c0 = true;
c@41:     m_mfcc = new MFCC(config);
c@41:     
c@41:     for (int i = 0; i < m_channels; ++i) {
c@41:         m_mfeatures.push_back(MFCCFeatureVector());
c@41:     }
c@41: 
c@41:     return true;
c@41: }
c@41: 
c@41: void
c@41: SimilarityPlugin::reset()
c@41: {
c@41:     //!!!
c@41: }
c@41: 
c@41: int
c@41: SimilarityPlugin::getDecimationFactor() const
c@41: {
c@41:     int rate = lrintf(m_inputSampleRate);
c@41:     int internalRate = 22050;
c@41:     int decimationFactor = rate / internalRate;
c@41:     if (decimationFactor < 1) decimationFactor = 1;
c@41: 
c@41:     // must be a power of two
c@41:     while (decimationFactor & (decimationFactor - 1)) ++decimationFactor;
c@41: 
c@41:     return decimationFactor;
c@41: }
c@41: 
c@41: size_t
c@41: SimilarityPlugin::getPreferredStepSize() const
c@41: {
c@41:     return 1024 * getDecimationFactor();
c@41: }
c@41: 
c@41: size_t
c@41: SimilarityPlugin::getPreferredBlockSize() const
c@41: {
c@41:     return 2048 * getDecimationFactor();
c@41: }
c@41: 
c@41: SimilarityPlugin::ParameterList SimilarityPlugin::getParameterDescriptors() const
c@41: {
c@41:     ParameterList list;
c@41:     return list;
c@41: }
c@41: 
c@41: float
c@41: SimilarityPlugin::getParameter(std::string param) const
c@41: {
c@41:     std::cerr << "WARNING: SimilarityPlugin::getParameter: unknown parameter \""
c@41:               << param << "\"" << std::endl;
c@41:     return 0.0;
c@41: }
c@41: 
c@41: void
c@41: SimilarityPlugin::setParameter(std::string param, float value)
c@41: {
c@41:     std::cerr << "WARNING: SimilarityPlugin::setParameter: unknown parameter \""
c@41:               << param << "\"" << std::endl;
c@41: }
c@41: 
c@41: SimilarityPlugin::OutputList
c@41: SimilarityPlugin::getOutputDescriptors() const
c@41: {
c@41:     OutputList list;
c@41: 	
c@41:     OutputDescriptor similarity;
c@41:     similarity.identifier = "distance";
c@41:     similarity.name = "Distance";
c@41:     similarity.description = "Distance Metric for Timbral Similarity (smaller = more similar)";
c@41:     similarity.unit = "";
c@41:     similarity.hasFixedBinCount = true;
c@41:     similarity.binCount = m_channels;
c@41:     similarity.hasKnownExtents = false;
c@41:     similarity.isQuantized = false;
c@41:     similarity.sampleType = OutputDescriptor::FixedSampleRate;
c@41:     similarity.sampleRate = 1;
c@41: 	
c@41:     list.push_back(similarity);
c@41: 	
c@41:     OutputDescriptor means;
c@41:     means.identifier = "means";
c@41:     means.name = "MFCC Means";
c@41:     means.description = "";
c@41:     means.unit = "";
c@41:     means.hasFixedBinCount = true;
c@41:     means.binCount = m_channels;
c@41:     means.hasKnownExtents = false;
c@41:     means.isQuantized = false;
c@41:     means.sampleType = OutputDescriptor::VariableSampleRate;
c@41:     means.sampleRate = m_inputSampleRate / getPreferredStepSize();
c@41: 	
c@41:     list.push_back(means);
c@41:     
c@41:     OutputDescriptor variances;
c@41:     variances.identifier = "variances";
c@41:     variances.name = "MFCC Variances";
c@41:     variances.description = "";
c@41:     variances.unit = "";
c@41:     variances.hasFixedBinCount = true;
c@41:     variances.binCount = m_channels;
c@41:     variances.hasKnownExtents = false;
c@41:     variances.isQuantized = false;
c@41:     variances.sampleType = OutputDescriptor::VariableSampleRate;
c@41:     variances.sampleRate = m_inputSampleRate / getPreferredStepSize();
c@41: 	
c@41:     list.push_back(variances);
c@41:     
c@41:     return list;
c@41: }
c@41: 
c@41: SimilarityPlugin::FeatureSet
c@41: SimilarityPlugin::process(const float *const *inputBuffers, Vamp::RealTime /* timestamp */)
c@41: {
c@41:     double *dblbuf = new double[m_blockSize];
c@41:     double *decbuf = dblbuf;
c@41:     if (m_decimator) decbuf = new double[m_mfcc->getfftlength()];
c@41:     double *ceps = new double[m_K];
c@41: 
c@41:     for (size_t c = 0; c < m_channels; ++c) {
c@41: 
c@41:         for (int i = 0; i < m_blockSize; ++i) {
c@41:             dblbuf[i] = inputBuffers[c][i];
c@41:         }
c@41: 
c@41:         if (m_decimator) {
c@41:             m_decimator->process(dblbuf, decbuf);
c@41:         }
c@41:         
c@41:         m_mfcc->process(m_mfcc->getfftlength(), decbuf, ceps);
c@41:         
c@41:         MFCCFeature mf(m_K);
c@41:         for (int i = 0; i < m_K; ++i) mf[i] = ceps[i];
c@41: 
c@41:         m_mfeatures[c].push_back(mf);
c@41:     }
c@41: 
c@41:     if (m_decimator) delete[] decbuf;
c@41:     delete[] dblbuf;
c@41:     delete[] ceps;
c@41: 	
c@41:     return FeatureSet();
c@41: }
c@41: 
c@41: SimilarityPlugin::FeatureSet
c@41: SimilarityPlugin::getRemainingFeatures()
c@41: {
c@41:     std::vector<MFCCFeature> m(m_channels);
c@41:     std::vector<MFCCFeature> v(m_channels);
c@41:     
c@41:     //!!! bail if m_mfeatures vectors are empty
c@41: 
c@41:     for (int i = 0; i < m_channels; ++i) {
c@41: 
c@41:         MFCCFeature mean(m_K), variance(m_K);
c@41: 
c@41:         for (int j = 0; j < m_K; ++j) {
c@41: 
c@41:             mean[j] = variance[j] = 0.0;
c@41:             int count;
c@41: 
c@41:             count = 0;
c@41:             for (int k = 0; k < m_mfeatures[i].size(); ++k) {
c@41:                 double val = m_mfeatures[i][k][j];
c@41: //                std::cout << "val = " << val << std::endl;
c@41:                 if (isnan(val) || isinf(val)) continue;
c@41:                 mean[j] += val;
c@41: //                std::cout << "mean now = " << mean[j] << std::endl;
c@41:                 ++count;
c@41:             }
c@41:             if (count > 0) mean[j] /= count;
c@41: //            std::cout << "divided by " << count << ", mean now " << mean[j] << std::endl;
c@41: 
c@41:             count = 0;
c@41:             for (int k = 0; k < m_mfeatures[i].size(); ++k) {
c@41:                 double val = ((m_mfeatures[i][k][j] - mean[j]) *
c@41:                               (m_mfeatures[i][k][j] - mean[j]));
c@41:                 if (isnan(val) || isinf(val)) continue;
c@41:                 variance[j] += val;
c@41:                 ++count;
c@41:             }
c@41:             if (count > 0) variance[j] /= count;
c@41:         }
c@41: 
c@41:         m[i] = mean;
c@41:         v[i] = variance;
c@41:     }
c@41: 
c@41: //    std::cout << "m[0][0] = " << m[0][0] << std::endl;
c@41: 
c@41:     // so we sorta return a matrix of the distances between channels,
c@41:     // but Vamp doesn't have a matrix return type so we actually
c@41:     // return a series of vectors
c@41: 
c@41:     std::vector<std::vector<double> > distances;
c@41: 
c@41:     for (int i = 0; i < m_channels; ++i) {
c@41:         distances.push_back(std::vector<double>());
c@41:         for (int j = 0; j < m_channels; ++j) {
c@41:             double d = -2.0 * m_K;
c@41:             for (int k = 0; k < m_K; ++k) {
c@41:                 // m[i][k] is the mean of mfcc k for channel i
c@41:                 // v[i][k] is the variance of mfcc k for channel i
c@41:                 d += v[i][k] / v[j][k] + v[j][k] / v[i][k];
c@41:                 d += (m[i][k] - m[j][k])
c@41:                     * (1.0 / v[i][k] + 1.0 / v[j][k])
c@41:                     * (m[i][k] - m[j][k]);
c@41:             }
c@41:             d /= 2.0;
c@41:             distances[i].push_back(d);
c@41:         }
c@41:     }
c@41: 
c@41:     FeatureSet returnFeatures;
c@41: 
c@41:     for (int i = 0; i < m_channels; ++i) {
c@41: 
c@41:         Feature feature;
c@41:         feature.hasTimestamp = true; // otherwise hosts will tend to stamp them at the end of the file, which is annoying
c@41:         feature.timestamp = Vamp::RealTime(i, 0);
c@41: 
c@41:         feature.values.clear();
c@41:         for (int k = 0; k < m_K; ++k) {
c@41:             feature.values.push_back(m[i][k]);
c@41:         }
c@41: 
c@41:         returnFeatures[1].push_back(feature);
c@41: 
c@41:         feature.values.clear();
c@41:         for (int k = 0; k < m_K; ++k) {
c@41:             feature.values.push_back(v[i][k]);
c@41:         }
c@41: 
c@41:         returnFeatures[2].push_back(feature);
c@41: 
c@41:         feature.values.clear();
c@41:         for (int j = 0; j < m_channels; ++j) {
c@41:             feature.values.push_back(distances[i][j]);
c@41:         }
c@41:         ostringstream oss;
c@41:         oss << "Distance from " << (i + 1);
c@41:         feature.label = oss.str();
c@41: 		
c@41:         returnFeatures[0].push_back(feature);
c@41:     }
c@41: 
c@41:     return returnFeatures;
c@41: }