aT.extract_features_and_train([root_data_path + "1/", root_data_path + "2/"], 1.0, 1.0, 0.2, 0.2, "svm", "temp", True) print("\n\n\n * * * TEST 5 * * * \n\n\n") [flagsInd, classesAll, acc, CM] = aS.mid_term_file_classification( root_data_path + "scottish.wav", root_data_path + "models/svm_rbf_sm", "svm_rbf", True, root_data_path + 'pyAudioAnalysis/data/scottish.segments') print("\n\n\n * * * TEST 6 * * * \n\n\n") aS.train_hmm_from_file(root_data_path + 'radioFinal/train/bbc4A.wav', root_data_path + 'radioFinal/train/bbc4A.segments', 'hmmTemp1', 1.0, 1.0) aS.train_hmm_from_directory(root_data_path + 'radioFinal/small', 'hmmTemp2', 1.0, 1.0) aS.hmm_segmentation(root_data_path + 'pyAudioAnalysis/data//scottish.wav', 'hmmTemp1', True, root_data_path + 'pyAudioAnalysis/data//scottish.segments') # test 1 aS.hmm_segmentation(root_data_path + 'pyAudioAnalysis/data//scottish.wav', 'hmmTemp2', True, root_data_path + 'pyAudioAnalysis/data//scottish.segments') # test 2 print("\n\n\n * * * TEST 7 * * * \n\n\n") aT.feature_extraction_train_regression(root_data_path + "pyAudioAnalysis/data/speechEmotion", 1, 1, 0.050, 0.050, "svm_rbf", "temp.mod", compute_beat=False)
def main(argv): if argv[1] == "-shortTerm": for i in range(nExp): [Fs, x] = audioBasicIO.read_audio_file("diarizationExample.wav") duration = x.shape[0] / float(Fs) t1 = time.time() F = MidTermFeatures.short_term_feature_extraction( x, Fs, 0.050 * Fs, 0.050 * Fs) t2 = time.time() perTime1 = duration / (t2 - t1) print "short-term feature extraction: {0:.1f} x realtime".format( perTime1) elif argv[1] == "-classifyFile": for i in range(nExp): [Fs, x] = audioBasicIO.read_audio_file("diarizationExample.wav") duration = x.shape[0] / float(Fs) t1 = time.time() aT.file_classification("diarizationExample.wav", "svmSM", "svm") t2 = time.time() perTime1 = duration / (t2 - t1) print "Mid-term feature extraction + classification \t {0:.1f} x realtime".format( perTime1) elif argv[1] == "-mtClassify": for i in range(nExp): [Fs, x] = audioBasicIO.read_audio_file("diarizationExample.wav") duration = x.shape[0] / float(Fs) t1 = time.time() [flagsInd, classesAll, acc] = aS.mid_term_file_classification("diarizationExample.wav", "svmSM", "svm", False, '') t2 = time.time() perTime1 = duration / (t2 - t1) print "Fix-sized classification - segmentation \t {0:.1f} x realtime".format( perTime1) elif argv[1] == "-hmmSegmentation": for i in range(nExp): [Fs, x] = audioBasicIO.read_audio_file("diarizationExample.wav") duration = x.shape[0] / float(Fs) t1 = time.time() aS.hmm_segmentation('diarizationExample.wav', 'hmmRadioSM', False, '') t2 = time.time() perTime1 = duration / (t2 - t1) print "HMM-based classification - segmentation \t {0:.1f} x realtime".format( perTime1) elif argv[1] == "-silenceRemoval": for i in range(nExp): [Fs, x] = audioBasicIO.read_audio_file("diarizationExample.wav") duration = x.shape[0] / float(Fs) t1 = time.time() [Fs, x] = audioBasicIO.read_audio_file("diarizationExample.wav") segments = aS.silence_removal(x, Fs, 0.050, 0.050, smooth_window=1.0, Weight=0.3, plot=False) t2 = time.time() perTime1 = duration / (t2 - t1) print "Silence removal \t {0:.1f} x realtime".format(perTime1) elif argv[1] == "-thumbnailing": for i in range(nExp): [Fs1, x1] = audioBasicIO.read_audio_file("scottish.wav") duration1 = x1.shape[0] / float(Fs1) t1 = time.time() [A1, A2, B1, B2, Smatrix] = aS.music_thumbnailing(x1, Fs1, 1.0, 1.0, 15.0) # find thumbnail endpoints t2 = time.time() perTime1 = duration1 / (t2 - t1) print "Thumbnail \t {0:.1f} x realtime".format(perTime1) elif argv[1] == "-diarization-noLDA": for i in range(nExp): [Fs1, x1] = audioBasicIO.read_audio_file("diarizationExample.wav") duration1 = x1.shape[0] / float(Fs1) t1 = time.time() aS.speaker_diarization("diarizationExample.wav", 4, LDAdim=0, PLOT=False) t2 = time.time() perTime1 = duration1 / (t2 - t1) print "Diarization \t {0:.1f} x realtime".format(perTime1) elif argv[1] == "-diarization-LDA": for i in range(nExp): [Fs1, x1] = audioBasicIO.read_audio_file("diarizationExample.wav") duration1 = x1.shape[0] / float(Fs1) t1 = time.time() aS.speaker_diarization("diarizationExample.wav", 4, PLOT=False) t2 = time.time() perTime1 = duration1 / (t2 - t1) print "Diarization \t {0:.1f} x realtime".format(perTime1)
def segmentclassifyFileWrapperHMM(wavFile, hmmModelName): gtFile = wavFile.replace(".wav", ".segments") aS.hmm_segmentation(wavFile, hmmModelName, plot_results=True, gt_file=gtFile)