with bug-fixed xsampa->ipa conversion, FA is performed.
yemaozi88
parent
df0e96c4f1
commit
3a98e184fe
Binary file not shown.
|
|
@ -9,14 +9,12 @@ Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Solution Items", "Solution
|
|||
ProjectSection(SolutionItems) = preProject
|
||||
..\forced_alignment\forced_alignment\__init__.py = ..\forced_alignment\forced_alignment\__init__.py
|
||||
..\forced_alignment\forced_alignment\convert_phone_set.py = ..\forced_alignment\forced_alignment\convert_phone_set.py
|
||||
..\ipa-xsama-converter\converter.py = ..\ipa-xsama-converter\converter.py
|
||||
..\forced_alignment\forced_alignment\defaultfiles.py = ..\forced_alignment\forced_alignment\defaultfiles.py
|
||||
..\toolbox\evaluation.py = ..\toolbox\evaluation.py
|
||||
..\forced_alignment\forced_alignment\forced_alignment.pyproj = ..\forced_alignment\forced_alignment\forced_alignment.pyproj
|
||||
..\forced_alignment\forced_alignment\htk_dict.py = ..\forced_alignment\forced_alignment\htk_dict.py
|
||||
..\forced_alignment\forced_alignment\lexicon.py = ..\forced_alignment\forced_alignment\lexicon.py
|
||||
..\forced_alignment\forced_alignment\mlf.py = ..\forced_alignment\forced_alignment\mlf.py
|
||||
..\accent_classification\accent_classification\output_confusion_matrix.py = ..\accent_classification\accent_classification\output_confusion_matrix.py
|
||||
..\forced_alignment\forced_alignment\pronunciations.py = ..\forced_alignment\forced_alignment\pronunciations.py
|
||||
..\toolbox\pyHTK.py = ..\toolbox\pyHTK.py
|
||||
..\forced_alignment\forced_alignment\pyhtk.py = ..\forced_alignment\forced_alignment\pyhtk.py
|
||||
..\forced_alignment\forced_alignment\scripts.py = ..\forced_alignment\forced_alignment\scripts.py
|
||||
..\forced_alignment\forced_alignment\tempfilename.py = ..\forced_alignment\forced_alignment\tempfilename.py
|
||||
|
|
|
|||
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -4,7 +4,7 @@
|
|||
<SchemaVersion>2.0</SchemaVersion>
|
||||
<ProjectGuid>4d8c8573-32f0-4a62-9e62-3ce5cc680390</ProjectGuid>
|
||||
<ProjectHome>.</ProjectHome>
|
||||
<StartupFile>phone_conversion_check.py</StartupFile>
|
||||
<StartupFile>performance_check.py</StartupFile>
|
||||
<SearchPath>
|
||||
</SearchPath>
|
||||
<WorkingDirectory>.</WorkingDirectory>
|
||||
|
|
@ -28,10 +28,13 @@
|
|||
<Compile Include="convert_xsampa2ipa.py">
|
||||
<SubType>Code</SubType>
|
||||
</Compile>
|
||||
<Compile Include="performance_check.py">
|
||||
<Compile Include="defaultfiles.py">
|
||||
<SubType>Code</SubType>
|
||||
</Compile>
|
||||
<Compile Include="phone_conversion_check.py">
|
||||
<Compile Include="fa_test.py">
|
||||
<SubType>Code</SubType>
|
||||
</Compile>
|
||||
<Compile Include="performance_check.py">
|
||||
<SubType>Code</SubType>
|
||||
</Compile>
|
||||
</ItemGroup>
|
||||
|
|
|
|||
|
|
@ -1,17 +1,13 @@
|
|||
import os
|
||||
import sys
|
||||
from collections import Counter
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
import defaultfiles as default
|
||||
|
||||
## ======================= user define =======================
|
||||
repo_dir = 'C:\\Users\\Aki\\source\\repos\\acoustic_model'
|
||||
curr_dir = repo_dir + '\\acoustic_model'
|
||||
forced_alignment_module = 'C:\\Users\\Aki\\source\\repos\\forced_alignment'
|
||||
|
||||
|
||||
sys.path.append(os.path.join(os.path.dirname(sys.path[0]), curr_dir))
|
||||
sys.path.append(forced_alignment_module)
|
||||
sys.path.append(default.forced_alignment_module_dir)
|
||||
from forced_alignment import convert_phone_set
|
||||
|
||||
|
||||
|
|
@ -42,6 +38,41 @@ def make_filelist(input_dir, output_txt):
|
|||
fout.write(input_dir + '\\' + filename + '\n')
|
||||
|
||||
|
||||
def make_dic(word, pronvar_, fileDic, output_type):
|
||||
"""
|
||||
make dict files which can be used for HTK.
|
||||
param word: target word.
|
||||
param pronvar_: pronunciation variant. nx2 (WORD /t pronunciation) ndarray.
|
||||
param fileDic: output dic file.
|
||||
param output_type: 0:full, 1:statistics, 2:frequency <2% entries are removed. 3:top 3.
|
||||
"""
|
||||
#assert(output_type < 4 and output_type >= 0, 'output_type should be an integer between 0 and 3.')
|
||||
WORD = word.upper()
|
||||
|
||||
if output_type == 0: # full
|
||||
pronvar = np.unique(pronvar_)
|
||||
|
||||
with open(fileDic, 'w') as f:
|
||||
for pvar in pronvar:
|
||||
f.write('{0}\t{1}\n'.format(WORD, pvar))
|
||||
else:
|
||||
c = Counter(pronvar_)
|
||||
total_num = sum(c.values())
|
||||
with open(fileDic, 'w') as f:
|
||||
if output_type == 3:
|
||||
for key, value in c.most_common(3):
|
||||
f.write('{0}\t{1}\n'.format(WORD, key))
|
||||
else:
|
||||
for key, value in c.items():
|
||||
percentage = value/total_num*100
|
||||
|
||||
if output_type == 1: # all
|
||||
f.write('{0}\t{1:.2f}\t{2}\t{3}\n'.format(value, percentage, WORD, key))
|
||||
elif output_type == 2: # less than 2 percent
|
||||
if percentage < 2:
|
||||
f.write('{0}\t{1}\n'.format(WORD, key))
|
||||
|
||||
|
||||
def get_phonelist(lexicon_file):
|
||||
""" Make a list of phones which appears in the lexicon. """
|
||||
|
||||
|
|
@ -99,4 +130,22 @@ def combine_lexicon(lexicon_file1, lexicon_file2, lexicon_out):
|
|||
lex2 = pd.read_table(lexicon_file2, names=['word', 'pronunciation'])
|
||||
lex = pd.concat([lex1, lex2])
|
||||
lex = lex.sort_values(by='word', ascending=True)
|
||||
lex.to_csv(lexicon_out, index=False, header=False, encoding="utf-8", sep='\t')
|
||||
lex.to_csv(lexicon_out, index=False, header=False, encoding="utf-8", sep='\t')
|
||||
|
||||
|
||||
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)
|
||||
|
|
|
|||
|
|
@ -7,122 +7,155 @@ import json
|
|||
import sys
|
||||
import os
|
||||
|
||||
|
||||
#sys.path.append(ipa_xsampa_converter_dir)
|
||||
#import converter
|
||||
import defaultfiles as default
|
||||
sys.path.append(os.path.join(default.repo_dir, 'forced_alignment'))
|
||||
from forced_alignment import convert_phone_set
|
||||
|
||||
|
||||
def load_converter(source, sink, ipa_xsampa_converter_dir):
|
||||
"""load the converter.
|
||||
source and sink are either of "ipa", "xsampa" or "sassc".
|
||||
"""
|
||||
choices = ["ipa", "xsampa", "sassc"]
|
||||
"""load the converter.
|
||||
source and sink are either of "ipa", "xsampa" or "sassc".
|
||||
"""
|
||||
choices = ["ipa", "xsampa", "sassc"]
|
||||
|
||||
# Validate params
|
||||
try:
|
||||
choice1 = choices.index(source)
|
||||
choice2 = choices.index(sink)
|
||||
if choice1 == choice2:
|
||||
print("source and destination format are the same.")
|
||||
except ValueError:
|
||||
print("source and destination should be one of [ipa xsampa sassc].")
|
||||
exit(1)
|
||||
|
||||
# Mappings from disk
|
||||
# some may not be used if source or sink is already IPA
|
||||
source_to_ipa = {}
|
||||
ipa_to_sink = {}
|
||||
# Validate params
|
||||
try:
|
||||
choice1 = choices.index(source)
|
||||
choice2 = choices.index(sink)
|
||||
if choice1 == choice2:
|
||||
print("source and destination format are the same.")
|
||||
except ValueError:
|
||||
print("source and destination should be one of [ipa xsampa sassc].")
|
||||
exit(1)
|
||||
|
||||
# Mappings from disk
|
||||
# some may not be used if source or sink is already IPA
|
||||
source_to_ipa = {}
|
||||
ipa_to_sink = {}
|
||||
|
||||
ipa_xsampa = []
|
||||
sassc_ipa = []
|
||||
ipa_xsampa = []
|
||||
sassc_ipa = []
|
||||
|
||||
# The IPAs that actually occur within SASSC
|
||||
sassc_active_ipa = {}
|
||||
# The IPAs that actually occur within SASSC
|
||||
sassc_active_ipa = {}
|
||||
|
||||
script_dir = os.path.dirname(os.path.realpath(__file__))
|
||||
script_dir = os.path.dirname(os.path.realpath(__file__))
|
||||
|
||||
with open(os.path.join(ipa_xsampa_converter_dir, "ipa_xsampa_map.json"), encoding="utf-8") as f:
|
||||
ipa_xsampa = json.load(f)
|
||||
with open(os.path.join(ipa_xsampa_converter_dir, "ipa_xsampa_map.json"), encoding="utf-8") as f:
|
||||
ipa_xsampa = json.load(f)
|
||||
|
||||
sassc_active = source == "sassc" or sink == "sassc"
|
||||
if sassc_active:
|
||||
with open(os.path.join(script_dir, "./sassc_ipa.json")) as f:
|
||||
sassc_ipa = json.load(f)
|
||||
for pair in sassc_ipa:
|
||||
for char in pair[1]:
|
||||
sassc_active_ipa[char] = 1
|
||||
sassc_active = source == "sassc" or sink == "sassc"
|
||||
if sassc_active:
|
||||
with open(os.path.join(script_dir, "./sassc_ipa.json")) as f:
|
||||
sassc_ipa = json.load(f)
|
||||
for pair in sassc_ipa:
|
||||
for char in pair[1]:
|
||||
sassc_active_ipa[char] = 1
|
||||
|
||||
if source == "xsampa":
|
||||
for pair in ipa_xsampa:
|
||||
source_to_ipa[pair[1]] = pair[0]
|
||||
elif source == "sassc":
|
||||
for pair in sassc_ipa:
|
||||
source_to_ipa[pair[0]] = pair[1]
|
||||
if source == "xsampa":
|
||||
for pair in ipa_xsampa:
|
||||
source_to_ipa[pair[1]] = pair[0]
|
||||
elif source == "sassc":
|
||||
for pair in sassc_ipa:
|
||||
source_to_ipa[pair[0]] = pair[1]
|
||||
|
||||
if sink == "xsampa":
|
||||
for pair in ipa_xsampa:
|
||||
ipa_to_sink[pair[0]] = pair[1]
|
||||
elif sink == "sassc":
|
||||
for pair in sassc_ipa:
|
||||
ipa_to_sink[pair[1]] = pair[0]
|
||||
if sink == "xsampa":
|
||||
for pair in ipa_xsampa:
|
||||
ipa_to_sink[pair[0]] = pair[1]
|
||||
elif sink == "sassc":
|
||||
for pair in sassc_ipa:
|
||||
ipa_to_sink[pair[1]] = pair[0]
|
||||
|
||||
# Combine them into a single mapping
|
||||
mapping = {}
|
||||
if source == "ipa":
|
||||
mapping = ipa_to_sink
|
||||
elif sink == "ipa":
|
||||
mapping = source_to_ipa
|
||||
else:
|
||||
for k, ipas in source_to_ipa.iteritems():
|
||||
map_out = ""
|
||||
failed = False
|
||||
for ipa in ipas:
|
||||
val = ipa_to_sink.get(ipa)
|
||||
if not val:
|
||||
failed = True
|
||||
break
|
||||
map_out += val
|
||||
mapping[k] = map_out if not failed else None
|
||||
# Combine them into a single mapping
|
||||
mapping = {}
|
||||
if source == "ipa":
|
||||
mapping = ipa_to_sink
|
||||
elif sink == "ipa":
|
||||
mapping = source_to_ipa
|
||||
else:
|
||||
for k, ipas in source_to_ipa.iteritems():
|
||||
map_out = ""
|
||||
failed = False
|
||||
for ipa in ipas:
|
||||
val = ipa_to_sink.get(ipa)
|
||||
if not val:
|
||||
failed = True
|
||||
break
|
||||
map_out += val
|
||||
mapping[k] = map_out if not failed else None
|
||||
|
||||
return mapping
|
||||
return mapping
|
||||
|
||||
|
||||
def conversion(source, sink, mapping, line):
|
||||
"""
|
||||
conversion.
|
||||
Args:
|
||||
mapping: can be obtained with load_converter().
|
||||
line: must be seperated, by default the seperator is whitespace.
|
||||
"""
|
||||
"""
|
||||
conversion.
|
||||
Args:
|
||||
mapping: can be obtained with load_converter().
|
||||
line: must be seperated, by default the seperator is whitespace.
|
||||
"""
|
||||
|
||||
# Edit this to change the seperator
|
||||
SEPERATOR = " "
|
||||
# Edit this to change the seperator
|
||||
SEPERATOR = " "
|
||||
|
||||
line = line.strip()
|
||||
output = []
|
||||
#if sassc_active:
|
||||
# tokens = line.split(SEPERATOR)
|
||||
#else:
|
||||
tokens = line
|
||||
for token in tokens:
|
||||
if token.isspace():
|
||||
output.append(token)
|
||||
continue
|
||||
# Remove extraneous chars that IPA does not accept
|
||||
if sink == "sassc":
|
||||
cleaned_token = u""
|
||||
for char in token:
|
||||
if sassc_active_ipa.get(char):
|
||||
cleaned_token += char
|
||||
token = cleaned_token
|
||||
mapped = mapping.get(token)
|
||||
if not mapped:
|
||||
print("WARNING: could not map token ", token, file=sys.stderr)
|
||||
else:
|
||||
output.append(mapped)
|
||||
#if sassc_active:
|
||||
# output = SEPERATOR.join(output)
|
||||
#else:
|
||||
output = "".join(output)
|
||||
|
||||
return output
|
||||
line = line.strip()
|
||||
output = []
|
||||
#if sassc_active:
|
||||
# tokens = line.split(SEPERATOR)
|
||||
#else:
|
||||
tokens = line
|
||||
for token in tokens:
|
||||
if token.isspace():
|
||||
output.append(token)
|
||||
continue
|
||||
# Remove extraneous chars that IPA does not accept
|
||||
if sink == "sassc":
|
||||
cleaned_token = u""
|
||||
for char in token:
|
||||
if sassc_active_ipa.get(char):
|
||||
cleaned_token += char
|
||||
token = cleaned_token
|
||||
mapped = mapping.get(token)
|
||||
if not mapped:
|
||||
print("WARNING: could not map token ", token, file=sys.stderr)
|
||||
else:
|
||||
output.append(mapped)
|
||||
#if sassc_active:
|
||||
# output = SEPERATOR.join(output)
|
||||
#else:
|
||||
output = "".join(output)
|
||||
|
||||
return output
|
||||
|
||||
|
||||
def xsampa2ipa(mapping, xsampa):
|
||||
"""
|
||||
conversion from xsampa to ipa.
|
||||
|
||||
Args:
|
||||
mapping: can be obtained with load_converter().
|
||||
xsampa: a line written in xsampa.
|
||||
|
||||
Notes:
|
||||
function conversion does not work when:
|
||||
- the input is a word.
|
||||
- when the line includes '\'.
|
||||
- 'ɡ' and 'g' are considered to be different.
|
||||
|
||||
"""
|
||||
# make a multi_character_list to split 'xsampa'.
|
||||
multi_character_list = []
|
||||
for i in list(mapping):
|
||||
if len(i) > 1:
|
||||
multi_character_list.append(i)
|
||||
|
||||
# conversion
|
||||
ipa = []
|
||||
for phone in convert_phone_set.multi_character_tokenize(xsampa, multi_character_list):
|
||||
ipa.append(mapping.get(phone, phone))
|
||||
ipa = ''.join(ipa)
|
||||
|
||||
# strange conversion.
|
||||
ipa = ipa.replace('ɡ', 'g')
|
||||
|
||||
return ipa
|
||||
|
|
@ -0,0 +1,35 @@
|
|||
import os
|
||||
|
||||
#default_hvite_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'data', 'htk', 'config.HVite')
|
||||
|
||||
cygwin_dir = r'C:\cygwin64\home\Aki\acoustic_model'
|
||||
#config_hcopy = os.path.join(cygwin_dir, 'config', 'config.HCopy')
|
||||
#config_train = os.path.join(cygwin_dir, 'config', 'config.train')
|
||||
config_hvite = os.path.join(cygwin_dir, 'config', 'config.HVite')
|
||||
#mkhmmdefs_pl = os.path.join(cygwin_dir, 'src', 'acoustic_model', 'mkhmmdefs.pl')
|
||||
|
||||
#dbLexicon = C:\\Users\\Aki\\source\\repos\\rug_VS\\forced_alignment\\config\\lexicon.accdb
|
||||
#scriptBarbara = C:\\Users\\Aki\\source\\repos\\rug_VS\\forced_alignment\\config\\pronvars_barbara.perl
|
||||
#exeG2P = C:\\Users\\Aki\\source\\repos\\rug_VS\\forced_alignment\\config\\string2phon.exe
|
||||
|
||||
#[pyHTK]
|
||||
#configHVite = C:\\Users\\Aki\\source\\repos\\rug_VS\\forced_alignment\\config\\config.HVite
|
||||
#filePhoneList = C:\\Users\\Aki\\source\\repos\\rug_VS\\forced_alignment\\config\\phonelist_barbara.txt
|
||||
#AcousticModel = C:\\Users\\Aki\\source\\repos\\rug_VS\\forced_alignment\\config\\hmmdefs_16-2_barbara.compo
|
||||
|
||||
#dbLexicon = config['cLexicon']['dbLexicon']
|
||||
#scriptBarbara = config['cLexicon']['scriptBarbara']
|
||||
#exeG2P = config['cLexicon']['exeG2P']
|
||||
|
||||
#configHVite = config['pyHTK']['configHVite']
|
||||
#filePhoneList = config['pyHTK']['filePhoneList']
|
||||
#AcousticModel = config['pyHTK']['AcousticModel']
|
||||
|
||||
repo_dir = r'C:\Users\Aki\source\repos'
|
||||
ipa_xsampa_converter_dir = os.path.join(repo_dir, 'ipa-xsama-converter')
|
||||
forced_alignment_module_dir = os.path.join(repo_dir, 'forced_alignment')
|
||||
|
||||
fame_dir = r'C:\OneDrive\WSL\kaldi-trunk\egs\fame\s5\corpus'
|
||||
experiments_dir = r'c:\OneDrive\Research\rug\experiments'
|
||||
|
||||
phonelist = os.path.join(experiments_dir, 'friesian', 'acoustic_model', 'config', 'phonelist_friesian.txt')
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
import os
|
||||
import sys
|
||||
os.chdir(r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model')
|
||||
|
||||
import defaultfiles as default
|
||||
|
||||
sys.path.append(os.path.join(default.repo_dir, 'forced_alignment'))
|
||||
from forced_alignment import forced_alignment
|
||||
|
||||
wav_file = r'C:\Users\Aki\source\repos\forced_alignment\notebooks\sample\10147-1464186409-1917281.wav'
|
||||
forced_alignment(
|
||||
wav_file,
|
||||
#'Australië'
|
||||
'BUFFETCOUPON COULISSEN DOUANE'
|
||||
)
|
||||
|
||||
|
|
@ -1,255 +1,176 @@
|
|||
import os
|
||||
os.chdir(r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model')
|
||||
|
||||
import sys
|
||||
import csv
|
||||
import subprocess
|
||||
import configparser
|
||||
from collections import Counter
|
||||
import re
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import matplotlib.pyplot as plt
|
||||
from sklearn.metrics import confusion_matrix
|
||||
#from sklearn.metrics import confusion_matrix
|
||||
|
||||
|
||||
## ======================= 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)
|
||||
|
||||
|
||||
def make_dic(word, pronvar_, fileDic, output_type):
|
||||
"""
|
||||
make dict files which can be used for HTK.
|
||||
param word: target word.
|
||||
param pronvar_: pronunciation variant. nx2 (WORD /t pronunciation) ndarray.
|
||||
param fileDic: output dic file.
|
||||
param output_type: 0:full, 1:statistics, 2:frequency <2% entries are removed. 3:top 3.
|
||||
"""
|
||||
#assert(output_type < 4 and output_type >= 0, 'output_type should be an integer between 0 and 3.')
|
||||
|
||||
if output_type == 0: # full
|
||||
pronvar = np.unique(pronvar_)
|
||||
|
||||
with open(fileDic, 'w') as f:
|
||||
for pvar in pronvar:
|
||||
f.write('{0}\t{1}\n'.format(WORD, pvar))
|
||||
else:
|
||||
c = Counter(pronvar_)
|
||||
total_num = sum(c.values())
|
||||
with open(fileDic, 'w') as f:
|
||||
if output_type == 3:
|
||||
for key, value in c.most_common(3):
|
||||
f.write('{0}\t{1}\n'.format(WORD, key))
|
||||
else:
|
||||
for key, value in c.items():
|
||||
percentage = value/total_num*100
|
||||
|
||||
if output_type == 1: # all
|
||||
f.write('{0}\t{1:.2f}\t{2}\t{3}\n'.format(value, percentage, WORD, key))
|
||||
elif output_type == 2: # less than 2 percent
|
||||
if percentage < 2:
|
||||
f.write('{0}\t{1}\n'.format(WORD, key))
|
||||
import acoustic_model_functions as am_func
|
||||
import convert_xsampa2ipa
|
||||
import defaultfiles as default
|
||||
|
||||
|
||||
## ======================= user define =======================
|
||||
curr_dir = r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model'
|
||||
config_ini = curr_dir + '\\config.ini'
|
||||
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'
|
||||
ipa_xsampa_converter_dir = r'C:\Users\Aki\source\repos\ipa-xsama-converter'
|
||||
accent_classification_dir = r'C:\Users\Aki\source\repos\accent_classification\accent_classification'
|
||||
#curr_dir = r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model'
|
||||
#config_ini = 'config.ini'
|
||||
#repo_dir = r'C:\Users\Aki\source\repos'
|
||||
#forced_alignment_module = repo_dir + '\\forced_alignment'
|
||||
#forced_alignment_module_old = repo_dir + '\\aki_tools'
|
||||
#ipa_xsampa_converter_dir = repo_dir + '\\ipa-xsama-converter'
|
||||
#accent_classification_dir = repo_dir + '\\accent_classification\accent_classification'
|
||||
excel_file = os.path.join(default.experiments_dir, 'stimmen', 'data', 'Frisian Variants Picture Task Stimmen.xlsx')
|
||||
|
||||
|
||||
experiments_dir = r'C:\OneDrive\Research\rug\experiments'
|
||||
data_dir = experiments_dir + '\\stimmen\\data'
|
||||
csvfile = data_dir + '\\Frisian Variants Picture Task Stimmen.csv'
|
||||
#experiments_dir = r'C:\OneDrive\Research\rug\experiments'
|
||||
data_dir = os.path.join(default.experiments_dir, 'stimmen', 'data')
|
||||
#csvfile = data_dir + '\\Frisian Variants Picture Task Stimmen.csv'
|
||||
wav_dir = os.path.join(default.experiments_dir, 'stimmen', 'wav')
|
||||
acoustic_model_dir = os.path.join(default.experiments_dir, 'friesian', 'acoustic_model', 'model')
|
||||
htk_dict_dir = os.path.join(default.experiments_dir, 'stimmen', 'dic_short')
|
||||
fa_dir = os.path.join(default.experiments_dir, 'stimmen', 'FA')
|
||||
|
||||
#cygwin_dir = r'C:\cygwin64\home\Aki\acoustic_model'
|
||||
#lex_asr = os.path.join(default.fame_dir, 'lexicon', 'lex.asr')
|
||||
#lex_asr_htk = os.path.join(default.fame_dir, 'lexicon', 'lex.asr_htk')
|
||||
|
||||
cygwin_dir = r'C:\cygwin64\home\Aki\acoustic_model'
|
||||
|
||||
# procedure
|
||||
convert_phones = 0
|
||||
make_dic_files = 0
|
||||
make_dic_files_short = 0
|
||||
do_forced_alignment_htk = 0
|
||||
do_forced_alignment_htk = 1
|
||||
make_kaldi_data_files = 0
|
||||
make_kaldi_lexicon_txt = 0
|
||||
load_forced_alignment_kaldi = 1
|
||||
load_forced_alignment_kaldi = 0
|
||||
eval_forced_alignment = 0
|
||||
|
||||
|
||||
|
||||
## ======================= add paths =======================
|
||||
|
||||
sys.path.append(forced_alignment_module)
|
||||
sys.path.append(os.path.join(default.repo_dir, 'forced_alignment'))
|
||||
from forced_alignment import convert_phone_set
|
||||
from forced_alignment import pyhtk
|
||||
|
||||
# for interactive window
|
||||
sys.path.append(curr_dir)
|
||||
import convert_xsampa2ipa
|
||||
import acoustic_model_functions as am_func
|
||||
|
||||
# for forced-alignment
|
||||
sys.path.append(forced_alignment_module_old)
|
||||
import pyHTK
|
||||
|
||||
# to output confusion matrix
|
||||
sys.path.append(accent_classification_dir)
|
||||
from output_confusion_matrix import plot_confusion_matrix
|
||||
|
||||
|
||||
## ======================= 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'
|
||||
sys.path.append(os.path.join(default.repo_dir, 'toolbox'))
|
||||
#import pyHTK
|
||||
from evaluation import plot_confusion_matrix
|
||||
|
||||
|
||||
## ======================= convert phones ======================
|
||||
if convert_phones:
|
||||
mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', ipa_xsampa_converter_dir)
|
||||
|
||||
## check phones included in FAME!
|
||||
# the phones used in the lexicon.
|
||||
#phonelist = am_func.get_phonelist(lex_htk)
|
||||
mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', default.ipa_xsampa_converter_dir)
|
||||
|
||||
# the lines which include a specific phone.
|
||||
#lines = am_func.find_phone(lex_asr, 'x')
|
||||
xls = pd.ExcelFile(excel_file)
|
||||
|
||||
with open(csvfile, encoding="utf-8") as fin:
|
||||
lines = csv.reader(fin, delimiter=';', lineterminator="\n", skipinitialspace=True)
|
||||
next(lines, None) # skip the headers
|
||||
## check conversion
|
||||
#df = pd.read_excel(xls, 'frequency')
|
||||
#for xsampa, ipa in zip(df['X-SAMPA'], df['IPA']):
|
||||
# #ipa_converted = convert_xsampa2ipa.conversion('xsampa', 'ipa', mapping, xsampa_)
|
||||
# ipa_converted = convert_xsampa2ipa.xsampa2ipa(mapping, xsampa)
|
||||
# if not ipa_converted == ipa:
|
||||
# print('{0}: {1} - {2}'.format(xsampa, ipa_converted, ipa))
|
||||
|
||||
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)
|
||||
|
||||
# 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 phones included in FAME!
|
||||
# the phones used in the lexicon.
|
||||
#phonelist = am_func.get_phonelist(lex_asr)
|
||||
|
||||
# check if all phones are in the phonelist of the acoustic model.
|
||||
#phonelist = ' '.join(pronunciations)
|
||||
#np.unique(phonelist.split(' '))
|
||||
#phonelist.find(':')
|
||||
# the lines which include a specific phone.
|
||||
#lines = am_func.find_phone(lex_asr, 'x')
|
||||
|
||||
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')
|
||||
# Filename, Word, Self Xsampa
|
||||
df = pd.read_excel(xls, 'original')
|
||||
|
||||
pronunciations = np.load(data_dir + '\\pronunciations.npy')
|
||||
word_list = np.unique(words)
|
||||
ipas = []
|
||||
famehtks = []
|
||||
for xsampa in df['Self Xsampa']:
|
||||
if not isinstance(xsampa, float): # 'NaN'
|
||||
# typo?
|
||||
xsampa = xsampa.replace('r2:z@rA:\\t', 'r2:z@rA:t')
|
||||
xsampa = xsampa.replace(';', ':')
|
||||
|
||||
ipa = convert_xsampa2ipa.xsampa2ipa(mapping, xsampa)
|
||||
ipa = ipa.replace('ː', ':')
|
||||
ipa = ipa.replace(' ', '')
|
||||
ipas.append(ipa)
|
||||
famehtk = convert_phone_set.ipa2famehtk(ipa)
|
||||
famehtks.append(famehtk)
|
||||
else:
|
||||
ipas.append('')
|
||||
famehtks.append('')
|
||||
|
||||
# extract interesting cols.
|
||||
df = pd.DataFrame({'filename': df['Filename'],
|
||||
'word': df['Word'],
|
||||
'xsampa': df['Self Xsampa'],
|
||||
'ipa': pd.Series(ipas),
|
||||
'famehtk': pd.Series(famehtks)})
|
||||
# cleansing.
|
||||
df = df[~df['famehtk'].isin(['/', ''])]
|
||||
|
||||
|
||||
## ======================= make dict files used for HTK. ======================
|
||||
if make_dic_files:
|
||||
output_type = 2
|
||||
output_dir = experiments_dir + r'\stimmen\dic_short'
|
||||
word_list = np.unique(df['word'])
|
||||
|
||||
output_type = 3
|
||||
|
||||
for word in word_list:
|
||||
WORD = word.upper()
|
||||
fileDic = output_dir + '\\' + word + '.dic'
|
||||
htk_dict_file = htk_dict_dir + '\\' + word + '.dic'
|
||||
|
||||
# pronunciation variant of the target word.
|
||||
pronvar_ = pronunciations[words == word]
|
||||
# remove ''
|
||||
pronvar_ = np.delete(pronvar_, np.where(pronvar_==''))
|
||||
pronvar_ = df['famehtk'][df['word'].str.match(word)]
|
||||
|
||||
# make dic file.
|
||||
make_dic(word, pronvar_, fileDic, output_type)
|
||||
am_func.make_dic(word, pronvar_, htk_dict_file, output_type)
|
||||
|
||||
|
||||
## ======================= forced alignment using HTK =======================
|
||||
if do_forced_alignment_htk:
|
||||
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'
|
||||
|
||||
#hmm_num = 128
|
||||
for hmm_num in [1, 2, 4, 8, 16, 32, 64, 128, 256]:
|
||||
#hmm_num = 2
|
||||
for hmm_num in [1, 2, 4, 8, 16, 32, 64, 128, 256, 512, 1024]:
|
||||
|
||||
hmm_num_str = str(hmm_num)
|
||||
AcousticModel = experiments_dir + r'\friesian\acoustic_model\model\hmm' + hmm_num_str + r'-2\hmmdefs'
|
||||
acoustic_model = os.path.join(acoustic_model_dir, 'hmm' + hmm_num_str + r'-2\hmmdefs')
|
||||
|
||||
predictions = []
|
||||
file_num_max = len(filenames)
|
||||
for i in range(0, file_num_max):
|
||||
#for i in range(500, 502):
|
||||
print('=== {0}/{1} ==='.format(i, file_num_max))
|
||||
filename = filenames[i]
|
||||
fileWav = wav_dir + '\\' + filename
|
||||
for i, filename in enumerate(df['filename']):
|
||||
print('=== {0}/{1} ==='.format(i, len(df)))
|
||||
wav_file = os.path.join(wav_dir, filename)
|
||||
|
||||
if os.path.exists(fileWav):
|
||||
word = words[i]
|
||||
if os.path.exists(wav_file) and i in df['filename'].keys():
|
||||
word = df['word'][i]
|
||||
WORD = word.upper()
|
||||
|
||||
# make label file.
|
||||
fileLab = wav_dir + '\\' + filename.replace('.wav', '.lab')
|
||||
with open(fileLab, 'w') as f:
|
||||
label_file = os.path.join(wav_dir, filename.replace('.wav', '.lab'))
|
||||
with open(label_file, 'w') as f:
|
||||
lines = f.write(WORD)
|
||||
|
||||
fileDic = experiments_dir + r'\stimmen\dic_top3' + '\\' + word + '.dic'
|
||||
fileFA = experiments_dir + r'\stimmen\FA' + '\\' + filename.replace('.wav', '.txt') + hmm_num_str
|
||||
htk_dict_file = os.path.join(htk_dict_dir, word + '.dic')
|
||||
fa_file = os.path.join(fa_dir, filename.replace('.wav', '.txt') + hmm_num_str)
|
||||
pyhtk.doHVite(wav_file, label_file, htk_dict_file, fa_file, default.config_hvite, default.phonelist, acoustic_model)
|
||||
|
||||
pyHTK.doHVite(fileWav, fileLab, fileDic, fileFA, configHVite, filePhoneList, AcousticModel)
|
||||
prediction = read_fileFA(fileFA)
|
||||
prediction = am_func.read_fileFA(fa_file)
|
||||
predictions.append(prediction)
|
||||
|
||||
os.remove(fileLab)
|
||||
print('{0}: {1} -> {2}'.format(WORD, pronunciations[i], prediction))
|
||||
os.remove(label_file)
|
||||
print('{0}: {1} -> {2}'.format(WORD, df['famehtk'][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)
|
||||
#match = np.c_[words[predictions != ''], pronunciations[predictions != ''], predictions[predictions != '']]
|
||||
np.save(os.path.join(data_dir, 'predictions_hmm' + hmm_num_str + '.npy'), predictions)
|
||||
|
||||
|
||||
## ======================= make files which is used for forced alignment by Kaldi =======================
|
||||
|
|
@ -392,7 +313,7 @@ if make_kaldi_lexicon_txt:
|
|||
pronvar_list = np.unique(pronvar_list_)
|
||||
|
||||
for pronvar_ in pronvar_list:
|
||||
split_ipa = convert_phone_set.split_ipa_fame(pronvar_)
|
||||
split_ipa = convert_phone_set.split_fame_ipa(pronvar_)
|
||||
pronvar_out = ' '.join(split_ipa)
|
||||
pronvar_list_all.append([word, pronvar_out])
|
||||
|
||||
|
|
@ -456,13 +377,12 @@ if load_forced_alignment_kaldi:
|
|||
filename_ = filename
|
||||
|
||||
# correct or not.
|
||||
for filename, fa_pronunciation in zip(fa_filenames, fa_pronunciations):
|
||||
#for filename, fa_pronunciation in zip(fa_filenames, fa_pronunciations):
|
||||
|
||||
|
||||
|
||||
## ======================= evaluate the result of forced alignment =======================
|
||||
if eval_forced_alignment:
|
||||
|
||||
match_num = []
|
||||
for hmm_num in [1, 2, 4, 8, 16, 32, 64, 128, 256]:
|
||||
#hmm_num = 256
|
||||
|
|
|
|||
|
|
@ -1,54 +0,0 @@
|
|||
import os
|
||||
os.chdir(r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model')
|
||||
|
||||
import sys
|
||||
|
||||
import pandas as pd
|
||||
|
||||
|
||||
## ======================= user define =======================
|
||||
|
||||
forced_alignment_module = r'C:\Users\Aki\source\repos\forced_alignment'
|
||||
ipa_xsampa_converter_dir = r'C:\Users\Aki\source\repos\ipa-xsama-converter'
|
||||
|
||||
experiments_dir = r'c:\OneDrive\Research\rug\experiments'
|
||||
excel_file = experiments_dir + '\\stimmen\\data\\Frisian Variants Picture Task Stimmen.xlsx'
|
||||
|
||||
|
||||
## ======================= add paths =======================
|
||||
|
||||
sys.path.append(forced_alignment_module)
|
||||
from forced_alignment import convert_phone_set
|
||||
|
||||
import convert_xsampa2ipa
|
||||
|
||||
|
||||
xls = pd.ExcelFile(excel_file)
|
||||
df = pd.read_excel(xls, 'frequency')
|
||||
|
||||
mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', ipa_xsampa_converter_dir)
|
||||
|
||||
def xsampa2ipa(mapping, xsampa):
|
||||
# make a multi_character_list to split 'xsampa'.
|
||||
multi_character_list = []
|
||||
for i in list(mapping):
|
||||
if len(i) > 1:
|
||||
multi_character_list.append(i)
|
||||
|
||||
# conversion
|
||||
ipa = []
|
||||
for phone in convert_phone_set.multi_character_tokenize(xsampa, multi_character_list):
|
||||
ipa.append(mapping.get(phone, phone))
|
||||
ipa = ''.join(ipa)
|
||||
|
||||
# strange conversion.
|
||||
ipa = ipa.replace('ɡ', 'g')
|
||||
|
||||
return ipa
|
||||
|
||||
|
||||
for xsampa, ipa in zip(df['X-SAMPA'], df['IPA']):
|
||||
#ipa_converted = convert_xsampa2ipa.conversion('xsampa', 'ipa', mapping, xsampa_)
|
||||
ipa_converted = xsampa2ipa(mapping, xsampa)
|
||||
if not ipa_converted == ipa:
|
||||
print('{0}: {1} - {2}'.format(xsampa_, ipa_converted, ipa))
|
||||
Loading…
Reference in New Issue