p280427/acoustic_model
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

lexicon is made.

Browse Source
This commit is contained in:
yemaozi88
2019-01-29 21:52:11 +01:00
parent 8cda93de75
commit dc6b7b84b6
11 changed files with 241 additions and 424 deletions
Download Patch File Download Diff File Expand all files Collapse all files

104
acoustic_model/fame_hmm.py
View File

@ -5,7 +5,6 @@ os.chdir(r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model')
import tempfile
#import configparser
#import subprocess
#from collections import Counter
import time
import numpy as np
@ -29,44 +28,21 @@ dataset_list = ['devel', 'test', 'train']
# procedure
extract_features = 0
conv_lexicon = 1
#check_lexicon = 0
#make_mlf = 0
#combine_files = 0
#flat_start = 0
#train_model = 1
#sys.path.append(os.path.join(os.path.dirname(sys.path[0]), curr_dir))
#sys.path.append(forced_alignment_module)
#from forced_alignment import convert_phone_set
make_lexicon = 0
make_mlf = 0
combine_files = 0
flat_start = 0
train_model = 0
## ======================= load variables =======================
#config = configparser.ConfigParser()
#config.sections()
#config.read(config_ini)
#config_hcopy = config['Settings']['config_hcopy']
#config_train = config['Settings']['config_train']
#mkhmmdefs_pl = config['Settings']['mkhmmdefs_pl']
#FAME_dir = config['Settings']['FAME_dir']
#lexicon_dir = os.path.join(default.fame_dir, 'lexicon')
#lexicon_ipa = os.path.join(lexicon_dir, 'lex.ipa')
#lexicon_asr = os.path.join(lexicon_dir, 'lex.asr')
#lex_asr = FAME_dir + '\\lexicon\\lex.asr'
#lex_asr_htk = FAME_dir + '\\lexicon\\lex.asr_htk'
#lex_oov = FAME_dir + '\\lexicon\\lex.oov'
#lex_oov_htk = FAME_dir + '\\lexicon\\lex.oov_htk'
##lex_ipa = FAME_dir + '\\lexicon\\lex.ipa'
##lex_ipa_ = FAME_dir + '\\lexicon\\lex.ipa_'
##lex_ipa_htk = FAME_dir + '\\lexicon\\lex.ipa_htk'
#lex_htk = FAME_dir + '\\lexicon\\lex_original.htk'
#lex_htk_ = FAME_dir + '\\lexicon\\lex.htk'
lexicon_dir = os.path.join(default.fame_dir, 'lexicon')
lexicon_asr = os.path.join(lexicon_dir, 'lex.asr')
lexicon_oov = os.path.join(lexicon_dir, 'lex.oov')
lexicon_htk_asr = os.path.join(default.htk_dir, 'lexicon', 'lex.htk_asr')
lexicon_htk_oov = os.path.join(default.htk_dir, 'lexicon', 'lex.htk_oov')
lexicon_htk = os.path.join(default.htk_dir, 'lexicon', 'lex.htk')
#hcompv_scp = output_dir + '\\scp\\combined.scp'
#combined_mlf = output_dir + '\\label\\combined.mlf'
@ -88,8 +64,10 @@ if not os.path.exists(tmp_dir):
## ======================= extract features =======================
if extract_features:
print('==== extract features ====\n')
for dataset in dataset_list:
print('==== {} ===='.format(dataset))
print('==== dataset: {} ===='.format(dataset))
# a script file for HCopy
print(">>> making a script file for HCopy... \n")
@ -112,48 +90,28 @@ if extract_features:
fh.make_filelist(feature_dir_, hcompv_scp, '.mfc')
## ======================= convert lexicon from ipa to fame_htk =======================
if conv_lexicon:
print('==== convert lexicon from ipa 2 fame ====\n')
# convert each lexicon from ipa description to fame_htk phoneset.
#am_func.ipa2famehtk_lexicon(lex_oov, lex_oov_htk)
#am_func.ipa2famehtk_lexicon(lex_asr, lex_asr_htk)
## ======================= make lexicon for HTK =======================
if make_lexicon:
print('==== make lexicon for HTK ====\n')
# convert each lexicon from fame_asr phoneset to fame_htk phoneset.
print('>>> converting each lexicon from fame_asr phoneset to fame_htk phoneset... \n')
fame_functions.lexicon_asr2htk(lexicon_asr, lexicon_htk_asr)
fame_functions.lexicon_asr2htk(lexicon_oov, lexicon_htk_oov)
# combine lexicon
print('>>> combining lexicon files into one lexicon... \n')
# pronunciations which is not found in lex.asr are generated using G2P and listed in lex.oov.
# therefore there is no overlap between lex_asr and lex_oov.
#am_func.combine_lexicon(lex_asr_htk, lex_oov_htk, lex_htk)
fame_functions.combine_lexicon(lexicon_htk_asr, lexicon_htk_oov, lexicon_htk)
## ======================= check if all the phones are successfully converted =======================
if check_lexicon:
print("==== check if all the phones are successfully converted. ====\n")
# the phones used in the lexicon.
phonelist_asr = am_func.get_phonelist(lex_asr)
phonelist_oov = am_func.get_phonelist(lex_oov)
phonelist_htk = am_func.get_phonelist(lex_htk)
phonelist = phonelist_asr.union(phonelist_oov)
# the lines which include a specific phone.
lines = am_func.find_phone(lex_asr, 'g')
# statistics over the lexicon
lexicon_htk = pd.read_table(lex_htk, names=['word', 'pronunciation'])
pronunciation = lexicon_htk['pronunciation']
phones_all = []
for word in pronunciation:
phones_all = phones_all + word.split()
c = Counter(phones_all)
## =======================
## manually make changes to the pronunciation dictionary and save it as lex.htk
## =======================
# (1) Replace all tabs with single space;
# (2) Put a '\' before any dictionary entry beginning with single quote
#http://electroblaze.blogspot.nl/2013/03/understanding-htk-error-messages.html
## =======================
## manually make changes to the pronunciation dictionary and save it as lex.htk
## =======================
# (1) Replace all tabs with single space;
# (2) Put a '\' before any dictionary entry beginning with single quote
#http://electroblaze.blogspot.nl/2013/03/understanding-htk-error-messages.html
fame_functions.fix_single_quote(lexicon_htk)
## ======================= make label file =======================