音频流分割

这个代码是对音频分割聚类的一个代码，是从他人代码基础上做的，对音频的分割有一定的效果，里面有你想要的工程，如果你是做说话人识别或者语音分离，。

data
musicLargeData.mat
musicSmallData.mat
3WORDS.WAV
1WORD.WAV
diarizationExample.wav
4ClassStream.wav
4ClassStreamGT.mat
topGear.wav
topGearGT.mat
KingGeorgeSpeech_1939_small.wav
frequency.txt
DubaiAirport.wav
speech_music_sample.wav
KingGeorgeSpeech_1939_53sec.wav
BassClarinet_model1.wav
Clarinet
library
feature_spectral_zone.m
feature_mfccs.m
scaledBaumWelchContObs.m
scaledViterbiContObs.m
EM_pdf_est.m
scaledViterbiDisObs.m
scaledBaumWelchDisObs.m
scriptClassificationPerformance.m
fileClassification.m
em_alg_function.m
musicVisualizationDemoSOM.m
smithWaterman.m
musicMeterTempoInduction.m
dynamicTimeWarpingItakura.m
showHistogramFeatures2D.m
showHistogramFeatures.m
fftSNR.m
silenceDetectorUtterance.m
dynamicTimeWarpingSakoeChiba.m
musicThumbnailing.m
mtFileClassification.m
dctCompress.m
printPerformanceMeasures.m
dctDecompress.m
audioRecorderTimerCallback.m
audioRecorderOnline.m
mp3toWavDIR.m
fld.m
evaluateClassifier.m
modelSM.mat
modelSpeech.mat
computeBayesError.m
model4.mat
feature_spectral_rolloff.m
readWavFileScript.m
readWavFile.m
kNN_model_load.m
feature_spectral_flux.m
feature_zcr.m
modelMusicGenres3.mat
classifyKNN_D_Multi.m
segmentationPlotResults.m
mp3toWav.m
feature_energy_entropy.m
feature_mfccs_init.m
feature_energy.m
featureExtractionFile.m
fftExample.m
musicVisualizationDemo.m
stFeatureExtraction.m
segmentationSignalChange.m
mixturepdf.m
feature_chroma_vector.m
viterbiBestPath.m
viterbiTrainingMultiCo.m
viterbiTrainingMultiCoMix.m
stpFile.m
feature_harmonic.m
featureExtractionDir.m
segmentationProbSeq.m
computePerformanceMeasures.m
feature_spectral_entropy.m
plotFeaturesFile.m
feature_spectral_centroid.m
speakerDiarization.m
mtFeatureExtraction.m
segmentationCompareResults.m
getDFT.m
viterbiTrainingDo.m
model8.mat
kNN_model_add_class.m
soundOS.m
silenceRemoval.m
demos
outMFiles.png
matlabDependencyGraph.py
readme.html