def assistant():
name = texttospeech('how can I help you')
# Play audio "How can I help you?" in user's earphone
pa.play(name)
# Let the user record his/her input voice
filename = ra.record()
# Recognize and translate the user's input speech to text using IBM Bluemix NLP service
speech2=speechtotext(filename)
# speech2[0] returns the confidence of the text
# speech2[1] returns the text content
# We assume that when confidence > 0.25, the user records effective audio
if Speech2[0] > 0.25:
# i\If the user wants to set timer
if "time" in speech2[1]:
texttospeech('how many minutes')
pa.play('output.wav')
filename = ra.record()
speech2=speechtotext(filename)
if speech2[0] > 0.25:
settime = int(speech2[1])
set_timer(settime)
else:
texttospeech('Sorry I do not understand')
pa.play('output.wav')
# If the user wants to check the doneness of the food
elif 'check' in speech2[1]:
doneness = pm.well_done()
texttospeech(doneness)
pa.play('output.wav')
# If the user wants to recognize the food
elif 'recognize' in speech2[1]:
tmp = 'The labels for this object are'
label_list = pm.what_is_it()
for label in label_list:
tmp = tmp + str(label)
texttospeech(tmp)
pa.play('output.wav')
# We ignore all other kinds of input speech
else:
texttospeech('Sorry I do not understand')
pa.play('output.wav')
# The confidence value is too low, we ignore this input
else:
texttospeech('Sorry I do not understand')
pa.play('output.wav')
time.sleep(30)
audi = sys.argv[1]
else:
audi=input("Enter a wav file: ")
if len(audi) <= 1:
print("invalid input \n")
exit()
print("\n")
if (audi == 'rec' and len(sys.argv[2]) ):
if sys.argv[2].isdigit():
seconds = int(sys.argv[2])
tmpa = " recording : " +str(seconds)+"s"
print(tmpa)x
spinner.start(tmpa)
record = ra.record(seconds, "audio.wav")
spinner.stop()
print(" saved file name : ", record , "\n\n")
audi =record
else:
print("invalid input \n")
exit()
spinner.start(" analysing audio ...")
filename = audi
n_speakers = -1
#This will be the file name the user's attempt will be saved in
filename = DIR_PATH + "/file" + str(num_files) + ".wav"
#Prompt user to begin recording
record_msg = "Click to start recording.\n" + \
"Press Control-C while in the command line application to stop recording\n" + \
("Otherwise, recording will stop after %d seconds." % record_audio.RECORD_SECONDS)
g.msgbox(record_msg, ok_button = "Begin Recording")
except Exception as e:
print "Could not create GUI", e
#Fall back to command line interface
enter = raw_input("Press Enter to record...")
print "Recording audio..."
record_audio.record(filename)
print "recorded audio"
#Allow user to analyze an existing file
if len(sys.argv) >= 2:
filename = sys.argv[1]
downsample = 1
samplerate = 44100 // downsample
if len( sys.argv ) > 2: samplerate = int(sys.argv[2])
win_s = 4096 // downsample # fft size
hop_s = 512 // downsample # hop size
s = source(filename, samplerate, hop_s)
samplerate = s.samplerate
import warnings
warnings.filterwarnings("ignore")
print('Recording begins in 3 seconds ...')
time.sleep(3)
# load the model from disk
loaded_classifier = pickle.load(open('finalised_model.sav', 'rb'))
from live_extraction import extract_features
from record_audio import record
path = "C:\\Users\\Atulya\Documents\\GitHub\\gender-classifier-using-voice\\ML_final\\"
record(path)
extract_features(path)
# Importing the libraries
import pandas as pd
import numpy as np
#Importing the dataset
original_dataset = pd.read_csv('features.csv')
test_dataset = pd.read_csv('recorded_audio_features.csv')
original_dataset = original_dataset.iloc[:, 1:-1]
test_dataset = test_dataset.iloc[:, 1:]
appended_dataset = original_dataset.append(test_dataset)
import warnings
warnings.filterwarnings("ignore")
import time
from record_audio import record
modelpath = "speaker_models/"
gmm_files = [
os.path.join(modelpath, fname) for fname in os.listdir(modelpath)
if fname.endswith('.gmm')
]
#Load the Gaussian gender Models
models = [cPickle.load(open(fname, 'r')) for fname in gmm_files]
speakers = [fname.split("/")[-1].split(".gmm")[0] for fname in gmm_files]
# Read the test directory and get the list of test audio files
sr, audio = record()
vector = extract_features(audio, sr)
log_likelihood = np.zeros(len(models))
for i in range(len(models)):
gmm = models[i] #checking with each model one by one
scores = np.array(gmm.score(vector))
log_likelihood[i] = scores.sum()
winner = np.argmax(log_likelihood)
print "\nDetected as - ", speakers[winner]
time.sleep(1.0)