def initialize_unit(self, unit_type='XIF'):
"""
初始化基元
:param unit_type: 基元类型
:return:
"""
unit_type_path = unit + unit_type
self.__unit_type = unit_type
if os.path.exists(unit_type_path) is False:
raise FileExistsError('Error: 基元文件%s不存在' % unit_type)
else:
if os.path.exists(path_parameter + unit_type) is False:
os.mkdir(path_parameter + unit_type)
with open(unit_type_path) as f:
u = f.readline()
print('使用基元:', u)
print('载入基元中...')
while u:
u = f.readline()
if len(u) == 0:
break
u = u.strip('\n').split(',')
for i in range(len(u)):
'''状态集合'''
states = {_: u[i] for _ in range(self.__state_num)}
'''观测概率表示(GMM)'''
observations = ['GMM_probability']
'''状态转移矩阵'''
A = np.zeros((self.__state_num, self.__state_num))
'''开始状态，为虚状态，只允许向下一个状态转移'''
A[0][1] = 1.
for j in range(1, self.__state_num - 1):
for k in range(j, j + 2):
A[j][k] = 0.5
'''初始化GMM'''
gmm = [
Clustering.GMM(self.__vector_size, self.__mix_level)
for _ in range(self.__state_num - 2)
]
'''初始化虚状态评分类'''
virtual_gmm_1 = AcousticModel.VirtualState(0.)
virtual_gmm_2 = AcousticModel.VirtualState(0.)
gmm.insert(0, virtual_gmm_1)
gmm.append(virtual_gmm_2)
'''生成hmm实例'''
lhmm = LHMM(states, observations, None, A=A, profunc=gmm)
'''数据结构：{基元：[训练次数,HMM],}'''
self.__unit[u[i]] = [0, lhmm]
print('基元载入完成 √')
def generate(_unit):
""""""
'''状态集合'''
states = {_: _unit for _ in range(self.__state_num)}
'''观测概率表示(GMM)'''
observations = ['GMM_probability']
'''状态转移矩阵'''
A = np.zeros((self.__state_num, self.__state_num))
'''开始状态，为虚状态，只允许向下一个状态转移'''
A[0][1] = 1.
for j in range(1, self.__state_num - 1):
for k in range(j, j + 2):
A[j][k] = 0.5
'''创建基元文件夹'''
unit_path = PARAMETERS_FILE_PATH + '/%s/%s' % (self.__unit_type,
_unit)
if not os.path.exists(unit_path):
os.mkdir(unit_path)
'''''' '''''' ''''''
log = Log(self.__unit_type, _unit, console=self.__console)
if new_log:
log.generate()
else:
log.append()
'''初始化GMM'''
gmm = [
Clustering.GMM(self.__vector_size, self.__mix_level, log)
for _ in range(self.__state_num - 2)
]
'''初始化虚状态评分类'''
virtual_gmm_1 = AcousticModel.VirtualState(0.)
virtual_gmm_2 = AcousticModel.VirtualState(0.)
gmm.insert(0, virtual_gmm_1)
gmm.append(virtual_gmm_2)
'''生成hmm实例'''
lhmm = LHMM(states,
observations,
log,
T=None,
A=A,
profunc=gmm,
pi=None)
'''数据结构：{基元：HMM,...}'''
self.__unit[_unit] = lhmm
def viterbi(self, complex_states, complex_transmat, complex_prob,
complex_pi):
"""
维特比切分
:param complex_states: 复合状态矩阵
:param complex_transmat: 复合状态转移矩阵
:param complex_prob: 复合观测矩阵
:param complex_pi: 复合初始概率矩阵
:return:
"""
'''维特比强制对齐'''
return LHMM.viterbi(self.log,
complex_states,
complex_transmat,
complex_prob,
complex_pi,
convert=True,
show_mark_state=True)
def multi_embedded_training_1(self, label, data, init, *args):
"""
多进程嵌入式训练HMM
:param label: 音频标注(基元为单位的列表[a,b,c,...])
:param data: 音频数据
:param init: 是否初始化
:param args: 其他参数(show_q、当前处理音频数、总音频数、fix_code)
:return:
"""
hmm_list = []
data_list = [data]
data_t_list = [len(data)]
'''为每个HMM计算观测概率密度'''
for unit in label:
hmm = self.init_unit(unit=unit, new_log=init)
self.init_parameter(unit, hmm=hmm)
hmm_list.append(hmm)
hmm.cal_observation_pro(data_list, data_t_list)
hmm.clear_data()
'''生成嵌入式HMM'''
complex_states, complex_transmat, complex_prob, complex_pi = self.embedded(
label, hmm_list, 0, 15)
embed_hmm = LHMM(complex_states,
self.__state_num,
self.log,
transmat=complex_transmat,
probmat=[complex_prob],
pi=complex_pi,
hmm_list=hmm_list,
fix_code=args[3])
embed_hmm.add_data(data_list)
embed_hmm.add_T(data_t_list)
embed_hmm.baulm_welch(show_q=args[0])
for index in range(len(label)):
self.__save_acc(label[index], hmm_list[index])
self.log.note('当前已处理音频：%d / %d' % (args[1], args[2]), cls='i')
'''关闭日志'''
self.log.close()
def viterbi(self, label, data_size, data_index):
"""
维特比切分
:param label: 标注
:param data_size: 数据长度
:param data_index: 数据索引
:return:
"""
complex_states, complex_observation, complex_A, complex_B, complex_π = self.embedded(
label, data_index, 31)
'''维特比强制对齐'''
return LHMM.viterbi(complex_states,
complex_observation,
complex_A,
complex_B,
complex_π,
O_size=data_size,
matrix=False,
convert=True,
end_state_back=False)
def init_unit(self, unit, new_log=True, fix_code=0):
"""
初始化基元，生成基元的复合数据结构
:param unit: 初始化指定基元
:param new_log: 是否删除先前日志
:param fix_code: 关闭参数更新，000=0 001=1 010=2 100=4...
:return:
"""
""""""
'''状态集合'''
states = {_: unit for _ in range(self.__state_num)}
'''状态转移矩阵'''
transmat = np.zeros((self.__state_num, self.__state_num))
'''开始状态，为虚状态，只允许向下一个状态转移'''
transmat[0][1] = 1.
for j in range(1, self.__state_num - 1):
transmat[j][j] = 0.5 # 第一个转移概率
transmat[j][j + 1] = 0.5 # 第二个转移概率
'''创建基元文件夹'''
unit_path = PARAMETERS_FILE_PATH + '/%s/%s' % (self.__unit_type, unit)
log_hmm_path = unit_path + '/HMM'
log_gmm_path = [
unit_path + '/GMM_%d' % gmm_id
for gmm_id in range(self.__state_num - 2)
]
try:
os.mkdir(unit_path)
except FileExistsError:
pass
try:
os.mkdir(log_hmm_path)
except FileExistsError:
pass
try:
for gmm_id in range(self.__state_num - 2):
os.mkdir(log_gmm_path[gmm_id])
except FileExistsError:
pass
'''''' '''''' ''''''
log_hmm = Log(self.__unit_type, log_hmm_path, console=self.__console)
log_gmm = [
Log(self.__unit_type,
path=log_gmm_path[gmm_id],
console=self.__console)
for gmm_id in range(self.__state_num - 2)
]
if new_log:
log_hmm.generate()
for gmm_id in range(self.__state_num - 2):
log_gmm[gmm_id].generate()
else:
log_hmm.append()
for gmm_id in range(self.__state_num - 2):
log_gmm[gmm_id].append()
'''初始化GMM'''
gmm = []
for gmm_id in range(self.__state_num - 2):
gmm.append(
Clustering.GMM(log_gmm[gmm_id],
dimension=self.__vector_size,
mix_level=self.__mix_level,
gmm_id=gmm_id))
'''初始化虚状态评分类'''
virtual_gmm_1 = AcousticModel.VirtualState(1.)
virtual_gmm_2 = AcousticModel.VirtualState(0.)
gmm.insert(0, virtual_gmm_1)
gmm.append(virtual_gmm_2)
'''生成hmm实例'''
lhmm = LHMM(states,
self.__state_num,
log_hmm,
transmat=transmat,
profunc=gmm,
fix_code=fix_code)
return lhmm