def train(self):
print 'train classifier'
trainer.featureAndTrain(
listOfDirs=self.class_dir_list,
mtWin=1.0,
mtStep=1.0,
stWin=trainer.shortTermWindow,
stStep=trainer.shortTermStep,
classifierType=self.classifier_type,
modelName=self.classifier_path
)
print 'classifier trained'
from pyAudioAnalysis import audioTrainTest as aT
aT.featureAndTrain([
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/_background_noise_",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/one",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/two",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/three",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/four",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/five",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/six",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/seven",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/eight",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/nine",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/yes",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/wav/speech_commands/no"
], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmSMtemp", False)
aT.fileClassification(
"/home/brandonjabr/pyAudio/pyAudioAnalysis/my-recordings/yes/1529689771.331.wav",
"svmSMtemp", "svm")
from pyAudioAnalysis import audioTrainTest as aT
aT.featureAndTrain(["classifierData/music","classifierData/speech"], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmSMtemp", False)
aT.fileClassification("data/doremi.wav", "svmSMtemp","svm")
from pyAudioAnalysis import audioTrainTest as aT
from pyAudioAnalysis import audioSegmentation as aS
from os import path
import os
import sys
modelName = sys.argv[
1] # Command line argument 1 is the name of the training model.
mtw = float(sys.argv[2]) # Command line argument 2 is the mid-term window.
mts = float(sys.argv[3]) # Command line argument 3 is the mid-term step.
aT.featureAndTrain(["SetA/Good/", "SetA/Bad/"], mtw, mts, aT.shortTermWindow,
aT.shortTermStep, modelName, "Models/" + modelName)
for fileName in [
f for f in os.listdir("SetB/Good/")
if path.isfile(path.join("SetB/Good/", f))
]:
print "Classification result for good file: " + fileName + " is " + aT.fileClassification(
"SetB/Good/" + fileName, "Models/" + modelName, modelName)
for fileName in [
f for f in os.listdir("SetB/Bad/")
if path.isfile(path.join("SetB/Bad/", f))
]:
print "Classification result for bad file: " + fileName + " is " + aT.fileClassification(
"SetB/Bad/" + fileName, "Models/" + modelName, modelName)
"sm", "movie8", "speakers", "speaker-gender",
"music-genre6", "4class"
],
help="Classification task")
args = parser.parse_args()
return args
if __name__ == '__main__':
args = parseArguments()
root_data_path = args.data_folder
classifier_type = args.classifier_type
if args.task == "sm":
aT.featureAndTrain(
[root_data_path + "SM/speech", root_data_path + "SM/music"], 1.0,
1.0, 0.05, 0.05, classifier_type, classifier_type + "_sm", False)
elif args.task == "movie8":
aT.featureAndTrain([
root_data_path + "movieSegments/8-class/Speech",
root_data_path + "movieSegments/8-class/Music",
root_data_path + "movieSegments/8-class/Others1",
root_data_path + "movieSegments/8-class/Others2",
root_data_path + "movieSegments/8-class/Others3",
root_data_path + "movieSegments/8-class/Shots",
root_data_path + "movieSegments/8-class/Fights",
root_data_path + "movieSegments/8-class/Screams"
], 1.0, 1.0, 0.05, 0.05, classifier_type,
classifier_type + "_movie8class", False)
elif args.task == "speakers":
aT.featureAndTrain([
import os
import sys
from pyAudioAnalysis import audioFeatureExtraction as aF
from pyAudioAnalysis import audioTrainTest as aT
from pyAudioAnalysis import audioBasicIO
#aT.featureAndTrain([""], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmMusicGenre3", True)
if __name__ =='__main__':
#train
aT.featureAndTrain(['Silence/','Speech/', 'Music/', 'Activity/'], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, 'svm', 'svmModelTest', False)
def train_slur_detector():
aT.featureAndTrain([os.path.join('/home', 'adi', 'HackDuke', 'Audio_Train','Normal'), os.path.join('/home', 'adi', 'HackDuke', 'Audio_Train','Slurred')], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, 'randomforest', 'rfTemp', False)
aT.featureAndTrain([os.path.join('/home', 'adi', 'HackDuke', 'Audio_Train','Normal'), os.path.join('/home', 'adi', 'HackDuke', 'Audio_Train','Slurred')], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, 'svm_rbf', 'svmRbfTemp', False)
def trainClassifierWrapper(method, beat_feats, directories, model_name):
if len(directories) < 2:
raise Exception("At least 2 directories are needed")
aT.featureAndTrain(directories, 1, 1, aT.shortTermWindow, aT.shortTermStep,
method.lower(), model_name, compute_beat=beat_feats)
# 模型的训练过程
from pyAudioAnalysis import audioTrainTest as aT
import nn
# 模型的名称和文件名
model = "svn"
modelName = "emotionModelData1SVN"
# 直接调用pyAudioAnalysis的包
# https://github.com/tyiannak/pyAudioAnalysis/wiki/4.-Classification-and-Regression
aT.featureAndTrain([
"/Users/aaa/Documents/python/wav/labels/angry",
"/Users/aaa/Documents/python/wav/labels/neutral"
], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, model, modelName, False)
# 训练神经网络模型的调用方法
#nn.trainNN(["/Users/aaa/Documents/python/wav/labels/angry",
# "/Users/aaa/Documents/python/wav/labels/neutral"],
# 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, False)
# 验证模型的准确率、召回率等
import os
from os import listdir
from os.path import isfile, join
# 测试音频的地址（文件夹）
dataPath = "/Users/aaa/Documents/python/wav/labels/test/"
files = [
join(dataPath, f) for f in listdir(dataPath) if isfile(join(dataPath, f))
]
print f
from pyAudioAnalysis import audioTrainTest as aT
aT.featureAndTrain(["./audio/metal", "./audio/dance"], 1.0, 1.0,
aT.shortTermWindow, aT.shortTermStep, "svm", "svmSMtemp",
False)
aT.featureAndTrain(
species,
# [
# "Bent-Beak-Riffraff",
# "Blue-collared-Zipper",
# "Bombadil",
# "Broad-winged-Jojo",
# "Canadian-Cootamum",
# "Carries-Champagne-Pipit",
# "Darkwing-Sparrow",
# "Eastern-Corn-Skeet",
# "Green-Tipped-Scarlet-Pipit",
# "Lesser-Birchbeere",
# "Orange-Pine-Plover",
# "Ordinary-Snape",
# "Pinkfinch",
# "Purple-Tooting-Tout",
# "Qax",
# "Queenscoat",
# "Rose-Crested-Blue-Pipit",
# "Scrawny-Jay",
# "Vermillion-Trillian",
# ],
1.0,
1.0,
aT.shortTermWindow,
aT.shortTermStep,
"svm",
"svmSMtemp",
False,
)
import os
from pyAudioAnalysis import audioTrainTest as aT
os.chdir('/export/home/u16/smcl/AAPB')
aT.featureAndTrain(['Reagan','test_set_616_clips'], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svm_Reagan_UBM_all", False)
aT.featureAndTrain(['Reagan','test_set_616_clips'], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "gradientboosting", "gradientboosting_Reagan_UBM_all", False)
aT.featureAndTrain(['Reagan','test_set_616_clips'], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "extratrees", "extratrees_Reagan_UBM_all", False)
aT.featureAndTrain(['Reagan','test_set_616_clips'], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "randomforest", "randomforest_Reagan_UBM_all", False)
aT.featureAndTrain(['Reagan','test_set_616_clips'], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "knn", "knn_Reagan_UBM_all", False)
import os
from pyAudioAnalysis import audioTrainTest as aT
os.chdir('/export/home/u16/smcl/AAPB')
aT.featureAndTrain(['Child','test_set_616_clips'], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svm_Child_UBM_all", False)
aT.featureAndTrain(['Child','test_set_616_clips'], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "gradientboosting", "gradientboosting_Child_UBM_all", False)
aT.featureAndTrain(['Child','test_set_616_clips'], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "extratrees", "extratrees_Child_UBM_all", False)
import sys
sys.path.append('C:\Python27\Lib\site-packages')
from pyAudioAnalysis import audioTrainTest as aT
import os
import pydub
pydub.AudioSegment.converter = r"C:\ffmpeg\bin"
import numpy as np
testData = "testData"
classifierData = [
"classifierData/cachorro", "classifierData/gato", "classifierData/onca"
]
# Fase de Treinamento
aT.featureAndTrain(classifierData, 1.0, 1.0, aT.shortTermWindow,
aT.shortTermStep, "svm", "svmSMtemp", False)
# Fase de Testes
fileout = open("result.txt", "w")
for filename in os.listdir(testData):
filename = testData + "/" + filename
Result, P, classNames = aT.fileClassification(filename, "svmSMtemp", "svm")
P = P * 100
winner = np.argmax(P) #pega o valor com a maior taxa de probabilidade.
print("Arquivo: " + filename + "; Animal: " + classNames[winner] +
"; Probabilidade: " + str(P[winner]) + "%")
fileout.write("Arquivo: " + filename + "; Animal: " + classNames[winner] +
"; Probabilidade: " + str(P[winner]) + "%\n")
fileout.close()
# 模型训练的调用 - 直接调用pyAudioAnalysis的函数，具体见voiceEmotionAnalysis.py
from pyAudioAnalysis import audioTrainTest as aT
aT.featureAndTrain([
"/Users/aaa/Documents/python/wav/labels/angry",
"/Users/aaa/Documents/python/wav/labels/neutral"
], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm",
"emotionModelData1SVM", False)
def train_deception_model(
truth_audio_path="../../training-data/deception-audio-datasets/truth_audio",
lie_audio_path="../../training-data/deception-audio-datasets/lie_audio_edited"
):
"""
developed by tybruno
This function was created to train the deception model using .wav files. Only .wav files are supported
:param truth_audio_path: path to the truth audio (.wav) datasets
:param lie_audio_path: path to the lie audio (.wav) datasets
:return:
"""
#train model
aT.featureAndTrain(
list_of_dirs=[truth_audio_path, lie_audio_path],
mt_win=1,
mt_step=1,
st_win=aT.shortTermWindow,
st_step=aT.shortTermStep,
classifier_type="svm",
model_name="deceptionSvm_edited",
compute_beat=False,
)
aT.featureAndTrain(
list_of_dirs=[truth_audio_path, lie_audio_path],
mt_win=1,
mt_step=1,
st_win=aT.shortTermWindow,
st_step=aT.shortTermStep,
classifier_type="knn",
model_name="deceptionKNN_edited",
compute_beat=False,
)
aT.featureAndTrain(
list_of_dirs=[truth_audio_path, lie_audio_path],
mt_win=1,
mt_step=1,
st_win=aT.shortTermWindow,
st_step=aT.shortTermStep,
classifier_type="randomforest",
model_name="deceptionRandomForest_edited",
compute_beat=False,
)
aT.featureAndTrain(
list_of_dirs=[truth_audio_path, lie_audio_path],
mt_win=1,
mt_step=1,
st_win=aT.shortTermWindow,
st_step=aT.shortTermStep,
classifier_type="gradientboosting",
model_name="deceptionGradientBoosting_edited",
compute_beat=False,
)
aT.featureAndTrain(
list_of_dirs=[truth_audio_path, lie_audio_path],
mt_win=1,
mt_step=1,
st_win=aT.shortTermWindow,
st_step=aT.shortTermStep,
classifier_type="extratrees",
model_name="deceptionExtraTrees_edited",
compute_beat=False,
)
import sys import os import numpy import shutil from pyAudioAnalysis import audioTrainTest as aT aT.featureAndTrain(["Python/pyAudioAnalysis-master/pyAudioAnalysis/classifierData/noise","Python/pyAudioAnalysis-master/pyAudioAnalysis/classifierData/speech","Python/pyAudioAnalysis-master/pyAudioAnalysis/classifierData/nothing"], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmSMtemp", False)
from pyAudioAnalysis import audioTrainTest as aT
#aT.featureAndTrain(["/home/tyiannak/Desktop/MusicGenre/Classical/","/home/tyiannak/Desktop/MusicGenre/Electronic/","/home/tyiannak/Desktop/MusicGenre/Jazz/"], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmMusicGenre3", True)
aT.featureAndTrain(
["pyAudioAnalysis/data/bones_music/", "pyAudioAnalysis/data/speech_vids/"],
1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmBones", False)
print aT.fileClassification(
"Intro_obtained_from_longest_common_subsequence.wav", "svmBones", "svm")
from pyAudioAnalysis import audioTrainTest as aT
aT.featureAndTrain([
"./categories/tecla_0", "./categories/tecla_1", "./categories/tecla_2",
"./categories/tecla_3", "./categories/tecla_4", "./categories/tecla_5",
"./categories/tecla_6", "./categories/tecla_7", "./categories/tecla_8",
"./categories/tecla_9"
], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmDTMF", False)
aT.featureAndTrain([
"./categories/tecla_0", "./categories/tecla_1", "./categories/tecla_2",
"./categories/tecla_3", "./categories/tecla_4", "./categories/tecla_5",
"./categories/tecla_6", "./categories/tecla_7", "./categories/tecla_8",
"./categories/tecla_9"
], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "knn", "knnDTMF", False)
# -*- coding: utf-8 -*- """ Spyder Editor """ from pyAudioAnalysis import audioTrainTest as aT import os dirname = '/home/hitesh/audioClassificationNew/trainingData' subdirectories = os.listdir(dirname)[:10] #subdirectories.pop(0) subdirectories = [dirname + "/" + subDirName for subDirName in subdirectories] print(subdirectories) aT.featureAndTrain(subdirectories, 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "newModel", False) ''' (list of directories,mid window size,mid window steps, short window size, short window step,type, file name to be saved,) Frequancy '''
from pyAudioAnalysis import audioTrainTest as aT
aT.featureAndTrain(["classifierData/snake","classifierData/Cheetah","classifierData/frog","classifierData/Fox","classifierData/seal","classifierData/panther","classifierData/tiger"], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmSMtemp", False)
aT.fileClassification("rattlesnake.wav", "svmSMtemp","svm")
#!/usr/local/bin/python2
from pyAudioAnalysis import audioTrainTest as aT
import os
from sys import argv
script, dirname = argv
subdirectories = os.listdir(dirname)[:5]
subdirectories.pop(0)
subdirectories = [dirname + "/" + subDirName for subDirName in subdirectories]
print(subdirectories)
aT.featureAndTrain(subdirectories, 1.0, 1.0, aT.shortTermWindow,
aT.shortTermStep, "svm", "svmModel", False)
from pyAudioAnalysis import audioTrainTest as aT aT.featureAndTrain(["./categories/tecla_0","./categories/tecla_1","./categories/tecla_2","./categories/tecla_3","./categories/tecla_4","./categories/tecla_5","./categories/tecla_6","./categories/tecla_7","./categories/tecla_8","./categories/tecla_9"], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmDTMF", False) aT.featureAndTrain(["./categories/tecla_0","./categories/tecla_1","./categories/tecla_2","./categories/tecla_3","./categories/tecla_4","./categories/tecla_5","./categories/tecla_6","./categories/tecla_7","./categories/tecla_8","./categories/tecla_9"], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "knn", "knnDTMF", False)
from pyAudioAnalysis import audioTrainTest as aT aT.featureAndTrain(["/var/www/html/data4/train/Artifact","/var/www/html/data4/train/Murmur","/var/www/html/data4/train/Normal"],0.125, 0.0625, aT.shortTermWindow, aT.shortTermStep, "svm", "/var/www/html/knnAll")
subdirectories = os.listdir(dirname)[:14] print (subdirectories) subdirectories = [dirname + "/" + subDirName for subDirName in subdirectories] print(subdirectories) #pyAudioAnalysis has 5 classifiers: # 1)SVM # 2)KNN # 3)randomForest # 4)GradientBoosting # 5)Extra Trees #SVM classifier used: aT.featureAndTrain(subdirectories, 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmModel", False) #KNN classifier used aT.featureAndTrain(subdirectories, 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "knn", "knnModel", False) #Extra Trees Model used aT.featureAndTrain(subdirectories, 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "extratrees", "extratreesModel", False) #Gradient Boosting classifier used aT.featureAndTrain(subdirectories, 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "gradientboosting", "gradientboostingModel", False) #RandomForest classifier used aT.featureAndTrain(subdirectories, 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "randomforest", "randomforestModel", False)
print("\n\n\n * * * TEST 2 * * * \n\n\n")
[Fs, x] = audioBasicIO.read_audio_file(root_data_path +
"pyAudioAnalysis/data/doremi.wav")
x = audioBasicIO.stereo_to_mono(x)
specgram, TimeAxis, FreqAxis = audioFeatureExtraction.stSpectogram(
x, Fs, round(Fs * 0.040), round(Fs * 0.040), True)
print("\n\n\n * * * TEST 3 * * * \n\n\n")
[Fs, x] = audioBasicIO.read_audio_file(root_data_path +
"pyAudioAnalysis/data/doremi.wav")
x = audioBasicIO.stereo_to_mono(x)
specgram, TimeAxis, FreqAxis = audioFeatureExtraction.stChromagram(
x, Fs, round(Fs * 0.040), round(Fs * 0.040), True)
print("\n\n\n * * * TEST 4 * * * \n\n\n")
aT.featureAndTrain([root_data_path + "SM/speech", root_data_path + "SM/music"],
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.mtFileClassification(
root_data_path + "pyAudioAnalysis/data//scottish.wav",
root_data_path + "pyAudioAnalysis/data/svmSM", "svm", True,
root_data_path + 'pyAudioAnalysis/data/scottish.segments')
print("\n\n\n * * * TEST 6 * * * \n\n\n")
aS.trainHMM_fromFile(root_data_path + 'radioFinal/train/bbc4A.wav',
root_data_path + 'radioFinal/train/bbc4A.segments',
'hmmTemp1', 1.0, 1.0)
aS.trainHMM_fromDir(root_data_path + 'radioFinal/small', 'hmmTemp2', 1.0, 1.0)
aS.hmmSegmentation(root_data_path + 'pyAudioAnalysis/data//scottish.wav',
'hmmTemp1', True, root_data_path +
'pyAudioAnalysis/data//scottish.segments') # test 1
os.system('mv ./data_interviewers/511_interviewer/'+i+' ./data_interviewers/511_interviewer_train/')
for i in wavs_511_interviewer[half:]:
os.system('mv ./data_interviewers/511_interviewer/'+i+' ./data_interviewers/511_interviewer_test/')
wavs_108_subset = os.listdir('./data_interviewers/108_subset/')
random.shuffle(wavs_108_subset )
half = int(len(wavs_108_subset )/2)
for i in wavs_108_subset[:half]:
os.system('mv ./data_interviewers/108_subset/'+i+' ./data_interviewers/108_subset_train/')
for i in wavs_108_subset[half:]:
os.system('mv ./data_interviewers/108_subset/'+i+' ./data_interviewers/108_subset_test/')
# Feature extraction
from pyAudioAnalysis import audioTrainTest as aT
aT.featureAndTrain(["./data_interviewers/511_interviewer_train/", "./data_interviewers/108_subset_train/"], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmSMtemp", False)
results= []
test_dir = './data_interviewers/108_subset_test/'
for interviewer_sample in os.listdir(test_dir):
results.append(aT.fileClassification(test_dir+interviewer_sample, "svmSMtemp","svm"))
y_pred = [n[0] for n in results]
import collections
counter=collections.Counter(y_pred)
print(counter)
Result:
(0.0, array([ 0.90156761, 0.09843239]), ['music', 'speech'])
import shutil
try:
shutil.rmtree('sciezki', ignore_errors=True)
except:
pass
try:
os.mkdir("sciezki")
except:
pass
client = Client('e-mail', 'password')
q = queue.Queue()
ficzery = [
"cisza", "alarm", "rakietybaza", "rakietydaleko", "tlumik", "ak", "c4",
"c4dalej", "statek", "helka"
]
aT.featureAndTrain(ficzery, 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep,
"svm", "svmSMtemp", False)
def callback(indata, frames, time, status):
"""This is called (from a separate thread) for each audio block."""
if status:
print(status, file=sys.stderr)
q.put(indata.copy())
device_info = sd.query_devices(2, 'input')
samplerate = int(device_info['default_samplerate'])
i = 0
try:
while (True):
with sf.SoundFile("sciezki/output{}.wav".format(i),
from pyAudioAnalysis import audioTrainTest as aT
aT.featureAndTrain(["classifierData/snake","classifierData/tiger"], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmSMtemp", False)
aT.fileClassification("snakehit.wav", "svmSMtemp","svm")
def trainClassifierWrapper(method, beat_feats, directories, model_name):
if len(directories) < 2:
raise Exception("At least 2 directories are needed")
aT.featureAndTrain(directories, 1, 1, aT.shortTermWindow, aT.shortTermStep,
method.lower(), model_name, compute_beat=beat_feats)
from pyAudioAnalysis import audioTrainTest as aT
aT.featureAndTrain([
"/home/brandonjabr/pyAudio/pyAudioAnalysis/my-recordings/highlights",
"/home/brandonjabr/pyAudio/pyAudioAnalysis/my-recordings/background"
], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svmSMtemp", False)
aT.fileClassification(
"/home/brandonjabr/pyAudio/pyAudioAnalysis/my-recordings/highlights/out-02.wav",
"svmSMtemp", "svm")
def main():
# def train():
input('Speak for 5 secs after pressing \'Enter\': ')
print('\nRecording')
time.sleep(.5)
frames = []
for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
data = stream.read(CHUNK)
frames.append(data)
print('\nRecording Saved.')
stream.stop_stream()
stream.close()
p.terminate()
wf = wave.open('sounds/' + 'output%d.wav' % FILE_NUMBER, 'wb')
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
wf.close()
# >>>>>>FEATURE EXTRACTION
[fs, x] = audioBasicIO.readAudioFile('sounds/output%d.wav' % FILE_NUMBER)
f, f_names = ShortTermFeatures.feature_extraction(x, fs, 0.050 * fs,
0.025 * fs)
print(f_names)
print(f)
# def trainClassifier():
# >>>>>TRAINING SVM
aT.featureAndTrain([
"Male/",
"Female/",
], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "svm2Classes")
aT.fileClassification('sounds/output1.wav', "svm2Classes", svm)
# def playAudio ():
# Play audio
input('To play audio press \'Enter\': ')
filename = 'sounds/output1.wav'
wave_obj = sa.WaveObject.from_wave_file(filename)
play_obj = wave_obj.play()
play_obj.wait_done() # Wait until sound has finished playing
print("Audio has finished playing")
# def manipulate():
[fs, x] = audioBasicIO.readAudioFile('sounds/output%d.wav' % FILE_NUMBER)
f, f_names = ShortTermFeatures.feature_extraction(x, fs, 0.050 * fs,
0.025 * fs)
input('To manipulate input press \'Enter\': ')
# Create an array of random numbers to use as the adversarial input
r = np.random.rand(68, 198)
print("Adversarial input\n", r)
# Create an empty array to allow the user to edit any feature they want.
s = (68, 198)
e = np.zeros(s)
print("Empty data\n", e)
# Print the feature values for the original audio clip
print("Audio clip\n", f)
# Multiply the original audio with manipulated data to see if it can misclassify
m = f * r
print("Manipulated data\n", m)
# def plotGraphs ():
# Plotting original input
plt.subplot(2, 2, 1)
plt.plot(f[0, :])
plt.xlabel('Original')
plt.ylabel(f_names[0])
# Plotting adversarial input
plt.subplot(2, 2, 2)
plt.plot(r[0, :])
plt.xlabel('Adversarial input')
# Plotting manipulated data
plt.subplot(2, 2, 3)
plt.plot(m[0, :])
plt.xlabel('manipulated data')
plt.show()
# Convert manipulated array back into wav
librosa.feature.inverse.mfcc_to_audio(m,
n_mels=128,
dct_type=2,
norm='ortho',
ref=1.0,
lifter=0,
**kwargs)
import numpy as np
import scipy as sp
import pydub
import matplotlib as plt
from pyAudioAnalysis import audioTrainTest as aT
# In[2]:
# Reading the dataset with .wav files
#sr, x = scipy.io.wavfile.read('/home/sarvpsin/Desktop/pyAudioAnalysis/pyAudioAnalysis/Data_mic/gun_shot_wav/102305.wav ')
# In[8]:
aT.featureAndTrain([
"/home/sarvpsin/Desktop/pyAudioAnalysis/pyAudioAnalysis/Data_mic/gun_shot_wav",
"/home/sarvpsin/Desktop/pyAudioAnalysis/pyAudioAnalysis/Data_mic/car_horn_wav"
], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "svm", "SVMTry", False)
# In[12]:
#train test split here
aT.fileClassification(
"/home/sarvpsin/Desktop/pyAudioAnalysis/pyAudioAnalysis/Data_mic/Handgun_sound_effect_1-youtube-NWezpZms1VA-140-192.wav",
"SVMTry", "svm")
# In[6]:
# knn
#accuracy and F1_score
from pyAudioAnalysis import audioTrainTest as aT
import argparse
import os
parser = argparse.ArgumentParser()
parser.add_argument("root", help="directory with training examples per bird",
type=str)
args = parser.parse_args()
birds = ['Trainings_b151', 'Trainings_b174', 'Trainings_b179', 'Trainings_DB12', 'Trainings_DB20', 'Trainings_DB30', 'Trainings_b73', 'Trainings_DB4']
'''
EG: aT.featureAndTrain(["Fragments/Shuffle/","Fragments/Silence/","Fragments/Micbeep/", "Fragments/Backgroundbird1/"],
1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "knn", "manxknn")
'''
if __name__ == "__main__":
root = args.root
for bird in birds:
bird_birds_dir = os.listdir(root + bird)
sound_fragmentdir_list = [root + '/' + bird + '/' + sound_dir
for sound_dir in bird_birds_dir
if len(os.listdir(root + '/' + bird + '/' + sound_dir)) > 1]
aT.featureAndTrain(sound_fragmentdir_list, 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "knn", "knnmodel" + bird)
import sys
import os
SCRIPT_DIR = os.path.dirname(__file__)
sys.path.append(SCRIPT_DIR + "/../pyAudioAnalysis")
from pyAudioAnalysis import audioTrainTest as aT
import os
from sys import argv
dirname = SCRIPT_DIR + "/../data/training/"
script, model_type = argv
model_filename = SCRIPT_DIR + "/../data/" + model_type
entries = os.listdir(dirname)
print("all entries: ", entries)
subdirectories = [i for i in entries if os.path.isdir(dirname + i)]
print("dirs only: ", subdirectories)
subdirectories = [dirname + subDirName for subDirName in subdirectories]
print("final dirs: ", subdirectories)
aT.featureAndTrain(subdirectories, 1.0, 1.0, aT.shortTermWindow,
aT.shortTermStep, model_type, model_filename, False)
import os
from pyAudioAnalysis import audioTrainTest as aT
from python_scripts import tools
import time
MODEL_TYPES = [
'knn', 'svm', 'svm_rbf', 'randomforest', 'gradientboosting', 'extratrees',
'Emotion7'
]
EMOTION_LIST = tools.MAP_EMOTION.values()
input_dir = 'output_by_emotion'
output_dir = 'Models'
model_name = 'Emotion7'
model_type = MODEL_TYPES[3]
output_name = model_type + model_name
path_base = os.path.join(os.path.dirname(os.getcwd()), input_dir)
dir_list = [os.path.join(path_base, emo) for emo in EMOTION_LIST]
begin = time.time()
aT.featureAndTrain(dir_list, 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep,
model_type, os.path.join(output_dir, output_name))
end = time.time()
print("Duration : {}".format(end - begin))
from pyAudioAnalysis import audioTrainTest as aT
myList = ['Austin/a','Austin/b','Austin/c','Austin/d','Austin/e','Austin/f','Austin/g','Austin/h','Austin/i','Austin/j','Austin/k','Austin/l','Austin/m','Austin/have','Austin/in','Austin/that','Austin/the',"Austin/toNew",'Austin/u','Austin/n']
aT.featureAndTrain(myList, 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, 'svm', 'svm', False)
def classify(classifier,myFile):
[result, p, classNames] = aT.fileClassification(myFile,classifier,classifier)
print result
print p
print classNames
maxI = maxIndex(p)
return classNames[maxI]
#print aT.fileClassification(myFile,classifier,classifier)
# print aT.fileClassification("Austin/a1.wav", classifier, classifier)
# print aT.fileClassification("Austin/f1.wav", classifier,classifier)
# print aT.fileClassification("Austin/h1.wav", classifier,classifier)
# print aT.fileClassification("Austin/u1.wav", classifier,classifier)
# print aT.fileClassification("Austin/c1.wav", classifier,classifier)
def maxIndex(a):
i = 0
maxInd = 0
maxProb = 0
for element in a:
if element > maxProb:
maxInd = i
maxProb = element
i = i + 1
return maxInd
def classifyFile(myFile):
print aT.fileClassification(myFile, 'svm', 'svm')
def parseArguments():
parser = argparse.ArgumentParser(prog='PROG')
parser.add_argument(
'-d',
'--data_folder',
nargs=None,
default=
"/Users/tyiannak/ResearchData/Audio Dataset/pyAudioAnalysisData/")
parser.add_argument('-c',
'--classifier_type',
nargs=None,
required=True,
choices=[
"knn", "svm", "svm_rbf", "randomforest",
"extratrees", "gradientboosting"
],
help="Classifier type")
args = parser.parse_args()
return args
if __name__ == '__main__':
args = parseArguments()
root_data_path = args.data_folder
classifier_type = args.classifier_type
classifier_path = "sm_" + classifier_type
aT.featureAndTrain(
[root_data_path + "SM/speech", root_data_path + "SM/music"], 1.0, 1.0,
0.2, 0.2, classifier_type, classifier_path, False)
from __future__ import print_function
from pyAudioAnalysis import audioBasicIO
from pyAudioAnalysis import audioFeatureExtraction
from pyAudioAnalysis import audioTrainTest as aT
from pyAudioAnalysis import audioSegmentation as aS
import matplotlib.pyplot as plt
import argparse
def parseArguments():
parser = argparse.ArgumentParser(prog='PROG')
parser.add_argument('-d' , '--data_folder', nargs=None, default="/Users/tyiannak/ResearchData/Audio Dataset/pyAudioAnalysisData/")
parser.add_argument('-c' , '--classifier_type', nargs=None, required=True,
choices = ["knn", "svm", "svm_rbf", "randomforest", "extratrees", "gradientboosting"],
help="Classifier type")
args = parser.parse_args()
return args
if __name__ == '__main__':
args = parseArguments()
root_data_path = args.data_folder
classifier_type = args.classifier_type
classifier_path = "sm_" + classifier_type
aT.featureAndTrain([root_data_path +"SM/speech",root_data_path + "SM/music"],
1.0, 1.0, 0.2, 0.2, classifier_type,
classifier_path, False)
#from scipy.io.wavfile import read
#import numpy as np
#a = read("testbarks.wav")
#x = np.array(a[1])
#w = np.fft.fft(x)
#freqs = np.fft.fftfreq(len(w))
#print(w)
import matplotlib
# Force matplotlib to not use any Xwindows backend.
matplotlib.use('Agg')
from pyAudioAnalysis import audioTrainTest as aT
aT.featureAndTrain(["/home/Project/train/Dog","/home/Project/train/Man","/home/Project/train/Clatter","/home/Project/train/Bang", "/home/Project/train/Lownoise"], 1.0, 1.0, aT.shortTermWindow, aT.shortTermStep, "knn", "testDogy", False)
#Clatter short
#test = aT.fileClassification("/home/Project/train/Clatter/clatter3.wav", "testDogx","knn")
#print("Expected: Clatter")
#print(test)
#Loud door knock
#test = aT.fileClassification("/home/Project/train/Clatter/2016-03-13_1341393.wav", "testDogx","knn")
#print("Expected: Clatter")
#print(test)
#Dropping on hard floor
#test = aT.fileClassification("/home/Project/train/Clatter/2016-01-14_1013132.wav", "testDogx","knn")
#print("Expected: Clatter")
#print(test)
#Bang, short thud
#test = aT.fileClassification("/home/Project/train/Bang/2016-01-13_0909361.wav", "testDogx","knn")
#print("Expected: Bang")
#print(test)
#Bang, Watery hit
F, f_names = audioFeatureExtraction.stFeatureExtraction(x, Fs, 0.050*Fs, 0.025*Fs);
plt.subplot(2,1,1); plt.plot(F[0,:]); plt.xlabel('Frame no'); plt.ylabel(f_names[0]);
plt.subplot(2,1,2); plt.plot(F[1,:]); plt.xlabel('Frame no'); plt.ylabel(f_names[1]); plt.show()
print("\n\n\n * * * TEST 2 * * * \n\n\n")
[Fs, x] = audioBasicIO.readAudioFile(root_data_path + "pyAudioAnalysis/data/doremi.wav")
x = audioBasicIO.stereo2mono(x)
specgram, TimeAxis, FreqAxis = audioFeatureExtraction.stSpectogram(x, Fs, round(Fs * 0.040), round(Fs * 0.040), True)
print("\n\n\n * * * TEST 3 * * * \n\n\n")
[Fs, x] = audioBasicIO.readAudioFile(root_data_path + "pyAudioAnalysis/data/doremi.wav")
x = audioBasicIO.stereo2mono(x)
specgram, TimeAxis, FreqAxis = audioFeatureExtraction.stChromagram(x, Fs, round(Fs * 0.040), round(Fs * 0.040), True)
print("\n\n\n * * * TEST 4 * * * \n\n\n")
aT.featureAndTrain([root_data_path +"SM/speech",root_data_path + "SM/music"], 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.mtFileClassification(root_data_path + "pyAudioAnalysis/data//scottish.wav", root_data_path + "pyAudioAnalysis/data/svmSM", "svm", True, root_data_path + 'pyAudioAnalysis/data/scottish.segments')
print("\n\n\n * * * TEST 6 * * * \n\n\n")
aS.trainHMM_fromFile(root_data_path + 'radioFinal/train/bbc4A.wav', root_data_path + 'radioFinal/train/bbc4A.segments', 'hmmTemp1', 1.0, 1.0)
aS.trainHMM_fromDir(root_data_path + 'radioFinal/small', 'hmmTemp2', 1.0, 1.0)
aS.hmmSegmentation(root_data_path + 'pyAudioAnalysis/data//scottish.wav', 'hmmTemp1', True, root_data_path + 'pyAudioAnalysis/data//scottish.segments') # test 1
aS.hmmSegmentation(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.featureAndTrainRegression(root_data_path + "pyAudioAnalysis/data/speechEmotion", 1, 1, 0.050, 0.050, "svm_rbf", "temp.mod", compute_beat=False)
print(aT.fileRegression(root_data_path + "pyAudioAnalysis/data/speechEmotion/01.wav", "temp.mod", "svm_rbf"))
print("\n\n\n * * * TEST 8 * * * \n\n\n")
