raw_data_select += raw_data[dom[0] * 256 * 2:dom[1] * 256 * 2]
file_en = wave.open("./temp_sound/input_voice.wav", "wb")
file_en.setnchannels(1)
file_en.setsampwidth(2)
file_en.setframerate(16000)
file_en.writeframes(raw_data_select)
file_en.close()
##main
if __name__ == '__main__':
order_text = ['开门', '关门', '打开', '关闭', '安静']
#训练
#datas = get_mfc_data('C:/Users/18341/Desktop/book/听觉/实验3-语音识别/语料/features/')
datas = get_mfc_data('F:/HIT/大三上/视听觉/lab3/组/gzx_sound_mfcc/')
#model = hmm.GaussianHMM(n_components = 5, n_iter = 20, tol = 0.01, covariance_type="diag")
hmms = dict()
for category in datas:
Qs = datas[category]
n_hidden = 6
model = hmm.GaussianHMM(n_components=5,
n_iter=20,
tol=0.01,
covariance_type="diag")
vstack_Qs = np.vstack(tuple(Qs[:-3]))
#print(tuple(Qs[:-3]))
#print('----------')
import numpy as np
from hmmlearn import hmm
from get_mfc_data import get_mfc_data
import struct
import numpy as np
import os
if __name__ == "__main__":
datas = get_mfc_data(
'C:/Users/18341/Desktop/book/听觉/实验3-语音识别/语料/features/')
hmms = dict()
for category in datas:
Qs = datas[category]
n_hidden = 6
model = hmm.GaussianHMM(n_components=5,
n_iter=5,
tol=0.01,
covariance_type="diag")
vstack_Qs = np.vstack(tuple(Qs[:-3]))
model.fit(vstack_Qs, [Q.shape[0] for Q in Qs[:-3]])
print('success fit')
hmms[category] = model
#test
correct_num = 0
for category in datas:
for test_sample in datas[category][-3:]:
print('real_category:', category)
max_score = -1 * np.inf
predict = -1