def take_user_input(self, list_task, flag):
#Speech_samples_required = ['One', 'Two','Three', 'Four', 'Zero']
Username = "******"
#frames = []
#dict = { 'Four': 4, 'One': 1, 'Three': 3, 'Two': 2, 'Zero': 0}
#for v, i in enumerate(Speech_samples_required):
#print("When ready, please press esc and say {}".format(i))
#kb.wait('esc')
#print(i)
#audio_file_plath = Record_audio.record_voice(Username, "0", "1" , 'team_data/')
self.prompt_menu(list_task, flag)
#kb.wait('esc')
audio_file_path = Record_audio.record_voice("userinput", "1", 1,
'team_data/')
features = Record_audio.get_features("team_data/1_userinput_1.wav",
sr=8000)
#print(list(features))
features1 = []
features1.append(features)
features2 = pd.DataFrame(features1)
# Extract features from the user input
#calling classify_input to get the prediction and confidence measure by giving features and model, you have to complete the classify_input method
#model = 0
digit, confidence = self.classify_input(features2, model_KNN)
print(digit[0], confidence)
digit, choice = self.confirm_input(digit[0], confidence, flag)
return digit, choice
def confirm_input(self, digit, confidence, flag):
if (confidence > T) and (digit < len(list_task[flag])):
return digit, list_task[flag][digit]
else:
print('Sorry we could not understand you, please reconfirm')
#list_task = shuffled list_task
Record_audio.play_audio("sorry_reconfirm.wav")
return self.take_user_input(list_task, flag)
def rec():
Speech_samples_required = [
'Zero',
'One',
'Two',
'Three',
'Four',
'Five',
'Six',
'Seven',
'Eight',
'Nine',
'yes',
'no',
]
Username = input("What is your ID? ")
#frames = []
dict = {
'Eight': 8,
'Four': 4,
'Nine': 9,
'One': 1,
'Seven': 7,
'Five': 5,
'Six': 6,
'Three': 3,
'Two': 2,
'Zero': 0,
'no': 11,
'yes': 10
}
confidence_array = np.zeros(12)
for v, i in enumerate(Speech_samples_required * 1):
print("When ready, please press esc and say {}".format(i))
kb.wait('esc')
print(i)
audio_file_path = Record_audio.record_voice(Username, dict[i], v,
"team_data/")
Record_audio.play_audio(audio_file_path)
#get_features in Record_audio.py should be completed
features = Record_audio.get_features(audio_file_path, sr=8000)
label = int(audio_file_path.split("/")[-1].split("_")[0])
#######use your classifier to return a confidence and predict for the input
#######digit is the prediction and confidence should be confidence measure
confidence, digit = 0, 0 #use the model you defined here to get the confidence and digit
if digit == label:
confidence_array[dict[i]] = confidence
else:
pass
print("Confidence : {} Prediction : {} label : {} ".format(
confidence, digit, label))
def take_user_input(self, list_task, flag):
self.prompt_menu(list_task, flag)
audio_file_path = Record_audio.record_voice("userinput", "1", 1, "./")
features = Record_audio.get_features(audio_file_path,
sr=8000,
n_mfcc=30,
n_mels=128,
frames=15)
digit, confidence = self.classify_input(features)
digit, choice = self.confirm_input(digit, confidence, flag)
return digit, choice
def completeTheClassification():
for filename in glob.iglob(
"/Users/madhukaruturi/Desktop/Madhu/AI-ML/AIML-Labs/Hackathon I/speech-data/*.wav"
):
featureDF.append(
Record_audio.get_features(filename,
sr=8000,
n_mfcc=30,
n_mels=128,
frames=15))
labelDF.append(os.path.basename(filename).split('_')[0])
def test(fileName):
deep_features = []
deep_features.append(
Record_audio.get_features(fileName,
sr=8000,
n_mfcc=30,
n_mels=128,
frames=15))
loadedModel = pickle.load(
open(
"/Users/madhukaruturi/Desktop/Madhu/AI-ML/AIML-Labs/Hackathon I/model.sav",
'rb'))
print(loadedModel.predict(deep_features))
#Will take arguments as user_name
#hardcoding sampling rate to 8000
#--user <user_name>
import Record_audio as rec
import sys
import keyboard as kb
sounds_to_record = ['Zero', 'One', 'Two', 'Three', 'Four', 'Five',
'Six', 'Seven', 'Eight', 'Nine', 'Yes', 'No']
if len(sys.argv) < 2:
print('Required syntax: python record_samples.py <user_name>')
exit
user = sys.argv[1]
print("\n-----Start the process to record samples for User:"******"\n\n--------------Starting to record samples for ", sounds_to_record[label])
for sample_id in range(0,5):
print('{}_{}_{}.wav'.format( label, user, sample_id))
print("\nPress 'n' when you are ready")
kb.wait('n')
rec.record_voice(user, label, sample_id, "group5_voice/" )
def record_tonic():
print("let's record a new sound\n")
rec.record_to_file('menu_sleeping_demo_dj.wav')
print("great, done!\n")
'Five': 5,
'Six': 6,
'Three': 3,
'Two': 2,
'Zero': 0,
'no': 11,
'yes': 10
}
confidence_array = np.zeros(12)
for v, i in enumerate(Speech_samples_required * 10):
print("When ready, please press esc and say {}".format(i))
kb.wait('esc')
print(i)
audio_file_path = Record_audio.record_voice(Username, dict[i], v,
"team_data/")
Record_audio.play_audio(audio_file_path)
#get_features in Record_audio.py should be completed
features = Record_audio.get_features(audio_file_path, sr=8000)
label = int(audio_file_path.split("/")[-1].split("_")[0])
#######use your classifier to return a confidence and predict for the input
#######digit is the prediction and confidence should be confidence measure
confidence, digit = 0, 0 #use the model you defined here to get the confidence and digit
if digit == label:
confidence_array[dict[i]] = confidence
else:
pass
def prompt_menu(self, list_task, flag): #flag = menu(0)/quantity(1)
Record_audio.play_audio(menu_prompts[flag])
Record_audio.play_audio("beep.wav")
for i in range(0, len(list_task[flag])):
print('say ' + str(i) + ' for ' + str(list_task[flag][i]))
'Seven',
'Eight',
'Nine',
'Zero',
'yes',
'no',
]
Username = input("What is your ID? ")
#frames = []
dict = {
'Eight': 8,
'Four': 4,
'Nine': 9,
'One': 1,
'Seven': 7,
'Five': 5,
'Six': 6,
'Three': 3,
'Two': 2,
'Zero': 0,
'no': 11,
'yes': 10
}
for v, i in enumerate(Speech_samples_required * 10):
print("When ready, please press esc and say {}".format(i))
kb.wait('esc')
print(i)
audio_file_plath = Record_audio.record_voice(Username, dict[i], v,
'team_data/')