2018-06-13 00:22:53 +02:00
|
|
|
|
import os
|
|
|
|
|
import sys
|
|
|
|
|
import csv
|
|
|
|
|
import subprocess
|
2018-06-18 00:15:50 +02:00
|
|
|
|
import configparser
|
2018-06-21 16:27:00 +02:00
|
|
|
|
from collections import Counter
|
2018-06-13 00:22:53 +02:00
|
|
|
|
|
|
|
|
|
import numpy as np
|
2018-06-18 00:15:50 +02:00
|
|
|
|
import pandas as pd
|
2018-06-21 16:27:00 +02:00
|
|
|
|
import matplotlib.pyplot as plt
|
2018-06-13 00:22:53 +02:00
|
|
|
|
|
|
|
|
|
|
2018-06-21 16:27:00 +02:00
|
|
|
|
## ======================= functions =======================
|
|
|
|
|
|
|
|
|
|
def read_fileFA(fileFA):
|
|
|
|
|
"""
|
|
|
|
|
read the result file of HTK forced alignment.
|
|
|
|
|
this function only works when input is one word.
|
|
|
|
|
"""
|
|
|
|
|
with open(fileFA, 'r') as f:
|
|
|
|
|
lines = f.read()
|
|
|
|
|
lines = lines.split('\n')
|
|
|
|
|
|
|
|
|
|
phones = []
|
|
|
|
|
for line in lines:
|
|
|
|
|
line_split = line.split()
|
|
|
|
|
if len(line_split) > 1:
|
|
|
|
|
phones.append(line_split[2])
|
|
|
|
|
|
|
|
|
|
return ' '.join(phones)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#####################
|
|
|
|
|
## USER DEFINE ##
|
|
|
|
|
#####################
|
2018-06-18 00:15:50 +02:00
|
|
|
|
curr_dir = r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model'
|
|
|
|
|
config_ini = curr_dir + '\\config.ini'
|
2018-06-21 16:27:00 +02:00
|
|
|
|
forced_alignment_module = r'C:\Users\Aki\source\repos\forced_alignment'
|
|
|
|
|
forced_alignment_module_old = r'C:\OneDrive\Research\rug\code\forced_alignment\forced_alignment'
|
2018-06-13 00:22:53 +02:00
|
|
|
|
ipa_xsampa_converter_dir = r'C:\Users\Aki\source\repos\ipa-xsama-converter'
|
2018-06-21 16:27:00 +02:00
|
|
|
|
|
2018-06-13 00:22:53 +02:00
|
|
|
|
csvfile = r"C:\OneDrive\Research\rug\stimmen\Frisian Variants Picture Task Stimmen.csv"
|
2018-06-21 16:27:00 +02:00
|
|
|
|
experiments_dir = r'C:\OneDrive\Research\rug\experiments'
|
|
|
|
|
data_dir = experiments_dir + '\\stimmen\\data'
|
|
|
|
|
cygwin_dir = r'C:\cygwin64\home\Aki\acoustic_model'
|
2018-06-13 00:22:53 +02:00
|
|
|
|
|
2018-06-18 00:15:50 +02:00
|
|
|
|
# procedure
|
2018-06-21 16:27:00 +02:00
|
|
|
|
convert_phones = 0
|
|
|
|
|
make_dic_files = 0
|
|
|
|
|
make_dic_files_short = 0
|
|
|
|
|
do_forced_alignment = 0
|
|
|
|
|
eval_forced_alignment = 1
|
|
|
|
|
|
2018-06-18 00:15:50 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## ======================= add paths =======================
|
2018-06-13 00:22:53 +02:00
|
|
|
|
|
|
|
|
|
sys.path.append(forced_alignment_module)
|
|
|
|
|
from forced_alignment import convert_phone_set
|
|
|
|
|
|
2018-06-18 00:15:50 +02:00
|
|
|
|
# for interactive window
|
|
|
|
|
sys.path.append(curr_dir)
|
|
|
|
|
import convert_xsampa2ipa
|
|
|
|
|
import acoustic_model_functions as am_func
|
|
|
|
|
|
2018-06-21 16:27:00 +02:00
|
|
|
|
# for forced-alignment
|
|
|
|
|
sys.path.append(forced_alignment_module_old)
|
|
|
|
|
import pyHTK
|
|
|
|
|
|
2018-06-18 00:15:50 +02:00
|
|
|
|
|
|
|
|
|
## ======================= load variables =======================
|
|
|
|
|
config = configparser.ConfigParser()
|
|
|
|
|
config.sections()
|
|
|
|
|
config.read(config_ini)
|
|
|
|
|
|
|
|
|
|
FAME_dir = config['Settings']['FAME_dir']
|
|
|
|
|
|
|
|
|
|
lex_asr = FAME_dir + '\\lexicon\\lex.asr'
|
|
|
|
|
lex_asr_htk = FAME_dir + '\\lexicon\\lex.asr_htk'
|
2018-06-13 00:22:53 +02:00
|
|
|
|
|
2018-06-18 00:15:50 +02:00
|
|
|
|
|
2018-06-21 16:27:00 +02:00
|
|
|
|
## ======================= convert phones ======================
|
|
|
|
|
if convert_phones:
|
|
|
|
|
mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', ipa_xsampa_converter_dir)
|
2018-06-18 00:15:50 +02:00
|
|
|
|
|
2018-06-21 16:27:00 +02:00
|
|
|
|
## check phones included in FAME!
|
|
|
|
|
# the phones used in the lexicon.
|
|
|
|
|
#phonelist = am_func.get_phonelist(lex_htk)
|
2018-06-18 00:15:50 +02:00
|
|
|
|
|
2018-06-21 16:27:00 +02:00
|
|
|
|
# the lines which include a specific phone.
|
|
|
|
|
#lines = am_func.find_phone(lex_asr, 'x')
|
2018-06-18 00:15:50 +02:00
|
|
|
|
|
2018-06-21 16:27:00 +02:00
|
|
|
|
with open(csvfile, encoding="utf-8") as fin:
|
|
|
|
|
lines = csv.reader(fin, delimiter=';', lineterminator="\n", skipinitialspace=True)
|
|
|
|
|
next(lines, None) # skip the headers
|
2018-06-13 00:22:53 +02:00
|
|
|
|
|
2018-06-21 16:27:00 +02:00
|
|
|
|
filenames = []
|
|
|
|
|
words = []
|
|
|
|
|
pronunciations = []
|
|
|
|
|
for line in lines:
|
|
|
|
|
if line[1] is not '' and len(line) > 5:
|
|
|
|
|
filenames.append(line[0])
|
|
|
|
|
words.append(line[1])
|
|
|
|
|
pron_xsampa = line[3]
|
|
|
|
|
pron_ipa = convert_xsampa2ipa.conversion('xsampa', 'ipa', mapping, pron_xsampa)
|
|
|
|
|
pron_ipa = pron_ipa.replace('ː', ':')
|
|
|
|
|
pron_famehtk = convert_phone_set.ipa2famehtk(pron_ipa)
|
2018-06-18 00:15:50 +02:00
|
|
|
|
|
2018-06-21 16:27:00 +02:00
|
|
|
|
# adjust to phones used in the acoustic model.
|
|
|
|
|
pron_famehtk = pron_famehtk.replace('sp', 'sil')
|
|
|
|
|
pron_famehtk = pron_famehtk.replace('ce :', 'ce') # because ceh is ignored.
|
|
|
|
|
pron_famehtk = pron_famehtk.replace('w :', 'wh')
|
|
|
|
|
pron_famehtk = pron_famehtk.replace('e :', 'eh')
|
|
|
|
|
pron_famehtk = pron_famehtk.replace('eh :', 'eh')
|
|
|
|
|
pron_famehtk = pron_famehtk.replace('ih :', 'ih')
|
|
|
|
|
|
|
|
|
|
#translation_key = {'sp': 'sil', 'ce :': 'ceh', 'w :': 'wh'}
|
|
|
|
|
#pron = []
|
|
|
|
|
#for phoneme in pron_famehtk.split(' '):
|
|
|
|
|
# pron.append(translation_key.get(phoneme, phoneme))
|
|
|
|
|
#pronunciations.append(' '.join(pron_famehtk))
|
|
|
|
|
pronunciations.append(pron_famehtk)
|
|
|
|
|
|
|
|
|
|
# check if all phones are in the phonelist of the acoustic model.
|
|
|
|
|
#phonelist = ' '.join(pronunciations)
|
|
|
|
|
#np.unique(phonelist.split(' '))
|
|
|
|
|
#phonelist.find(':')
|
|
|
|
|
|
|
|
|
|
filenames = np.array(filenames)
|
|
|
|
|
words = np.array(words)
|
|
|
|
|
pronunciations = np.array(pronunciations)
|
|
|
|
|
|
|
|
|
|
del line, lines
|
|
|
|
|
del pron_xsampa, pron_ipa, pron_famehtk
|
|
|
|
|
|
|
|
|
|
np.save(data_dir + '\\filenames.npy', filenames)
|
|
|
|
|
np.save(data_dir + '\\words.npy', words)
|
|
|
|
|
np.save(data_dir + '\\pronunciations.npy', pronunciations)
|
|
|
|
|
else:
|
|
|
|
|
filenames = np.load(data_dir + '\\filenames.npy')
|
|
|
|
|
words = np.load(data_dir + '\\words.npy')
|
|
|
|
|
|
|
|
|
|
pronunciations = np.load(data_dir + '\\pronunciations.npy')
|
2018-06-18 00:15:50 +02:00
|
|
|
|
word_list = np.unique(words)
|
2018-06-21 16:27:00 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## ======================= make dict files used for HTK. ======================
|
|
|
|
|
if make_dic_files:
|
|
|
|
|
output_dir = experiments_dir + r'\stimmen\dic'
|
|
|
|
|
|
|
|
|
|
for word in word_list:
|
|
|
|
|
WORD = word.upper()
|
|
|
|
|
fileDic = output_dir + '\\' + word + '.dic'
|
|
|
|
|
|
|
|
|
|
# make dic file.
|
|
|
|
|
pronvar_ = pronunciations[words == word]
|
|
|
|
|
pronvar = np.unique(pronvar_)
|
|
|
|
|
|
|
|
|
|
with open(fileDic, 'w') as f:
|
|
|
|
|
for pvar in pronvar:
|
|
|
|
|
f.write('{0}\t{1}\n'.format(WORD, pvar))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## ======================= make dict files for most popular words. ======================
|
|
|
|
|
if make_dic_files_short:
|
|
|
|
|
output_dir = experiments_dir + r'\stimmen\dic'
|
|
|
|
|
|
|
|
|
|
#word = word_list[3]
|
|
|
|
|
for word in word_list:
|
|
|
|
|
WORD = word.upper()
|
|
|
|
|
fileStat = output_dir + '\\' + word + '_stat.csv'
|
|
|
|
|
|
|
|
|
|
pronvar = pronunciations[words == word]
|
|
|
|
|
c = Counter(pronvar)
|
|
|
|
|
total_num = sum(c.values())
|
|
|
|
|
|
|
|
|
|
with open(fileStat, 'w') as f:
|
|
|
|
|
for key, value in c.items():
|
|
|
|
|
f.write('{0}\t{1:.2f}\t{2}\t{3}\n'.format(value, value/total_num*100, WORD, key))
|
2018-06-13 00:22:53 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## ======================= forced alignment =======================
|
2018-06-21 16:27:00 +02:00
|
|
|
|
if do_forced_alignment:
|
|
|
|
|
configHVite = cygwin_dir + r'\config\config.HVite'
|
|
|
|
|
filePhoneList = experiments_dir + r'\friesian\acoustic_model\config\phonelist_friesian.txt'
|
|
|
|
|
wav_dir = experiments_dir + r'\stimmen\wav'
|
|
|
|
|
|
|
|
|
|
#for hmm_num in [1, 2, 4, 8, 16, 32, 64, 128]:
|
|
|
|
|
for hmm_num in [64]:
|
|
|
|
|
hmm_num_str = str(hmm_num)
|
|
|
|
|
AcousticModel = experiments_dir + r'\friesian\acoustic_model\model\hmm' + hmm_num_str + r'-3\hmmdefs'
|
|
|
|
|
|
|
|
|
|
predictions = []
|
|
|
|
|
file_num_max = len(filenames)
|
|
|
|
|
for i in range(0, file_num_max):
|
|
|
|
|
print('=== {0}/{1} ==='.format(i, file_num_max))
|
|
|
|
|
filename = filenames[i]
|
|
|
|
|
fileWav = wav_dir + '\\' + filename
|
|
|
|
|
|
|
|
|
|
if os.path.exists(fileWav):
|
|
|
|
|
word = words[i]
|
|
|
|
|
WORD = word.upper()
|
|
|
|
|
|
|
|
|
|
# make label file.
|
|
|
|
|
fileLab = wav_dir + '\\' + filename.replace('.wav', '.lab')
|
|
|
|
|
with open(fileLab, 'w') as f:
|
|
|
|
|
lines = f.write(WORD)
|
|
|
|
|
|
|
|
|
|
fileDic = experiments_dir + r'\stimmen\dic_short' + '\\' + word + '.dic'
|
|
|
|
|
fileFA = experiments_dir + r'\stimmen\FA_short' + '\\' + filename.replace('.wav', '.txt') + hmm_num_str
|
|
|
|
|
|
|
|
|
|
pyHTK.doHVite(fileWav, fileLab, fileDic, fileFA, configHVite, filePhoneList, AcousticModel)
|
|
|
|
|
prediction = read_fileFA(fileFA)
|
|
|
|
|
predictions.append(prediction)
|
|
|
|
|
|
|
|
|
|
os.remove(fileLab)
|
|
|
|
|
print('{0}: {1} -> {2}'.format(WORD, pronunciations[i], prediction))
|
|
|
|
|
else:
|
|
|
|
|
predictions.append('')
|
|
|
|
|
print('!!!!! file not found.')
|
|
|
|
|
|
|
|
|
|
predictions = np.array(predictions)
|
|
|
|
|
match = np.c_[words[predictions != ''], pronunciations[predictions != ''], predictions[predictions != '']]
|
|
|
|
|
np.save(data_dir + '\\match_hmm' + hmm_num_str + '.npy', match)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## ======================= evaluate the result of forced alignment =======================
|
|
|
|
|
if eval_forced_alignment:
|
|
|
|
|
|
|
|
|
|
#for hmm_num in [1, 2, 4, 8, 16, 32, 64]:
|
|
|
|
|
hmm_num = 64
|
|
|
|
|
hmm_num_str = str(hmm_num)
|
|
|
|
|
match = np.load(data_dir + '\\match_hmm' + hmm_num_str + '.npy')
|
|
|
|
|
|
|
|
|
|
# use dic_short?
|
|
|
|
|
if 1:
|
|
|
|
|
pronunciation_variants = np.array(['WORD', 'pronunciation']).reshape(1, 2)
|
|
|
|
|
for word in word_list:
|
|
|
|
|
fileDic = experiments_dir + r'\stimmen\dic_short' + '\\' + word + '.dic'
|
|
|
|
|
pronunciation_variants = np.r_[pronunciation_variants, pyHTK.loadHTKdic(fileDic)]
|
|
|
|
|
|
|
|
|
|
match_short = []
|
|
|
|
|
for line in match:
|
|
|
|
|
word = line[0]
|
|
|
|
|
WORD = word.upper()
|
|
|
|
|
pronvar = pronunciation_variants[pronunciation_variants[:, 0] == word.upper(), 1]
|
|
|
|
|
|
|
|
|
|
if line[1] in pronvar:
|
|
|
|
|
match_short.append(line)
|
|
|
|
|
|
|
|
|
|
match_short = np.array(match_short)
|
|
|
|
|
match = np.copy(match_short)
|
|
|
|
|
|
|
|
|
|
# number of match
|
|
|
|
|
total_match = sum(match[:, 1] == match[:, 2])
|
|
|
|
|
print("{}: {}/{}".format(hmm_num_str, total_match, match.shape[0]))
|
|
|
|
|
|