fame_asr phoneset is added including reduced version and htk compatible version.

This commit is contained in:
yemaozi88 2019-01-28 12:34:20 +01:00
parent 87abbbb95a
commit 8cda93de75
14 changed files with 465 additions and 98 deletions

Binary file not shown.

View File

@ -32,7 +32,9 @@
<Compile Include="defaultfiles.py"> <Compile Include="defaultfiles.py">
<SubType>Code</SubType> <SubType>Code</SubType>
</Compile> </Compile>
<Compile Include="fame_phoneset.py"> <Compile Include="fame_asr.py" />
<Compile Include="fame_ipa.py" />
<Compile Include="fame_test.py">
<SubType>Code</SubType> <SubType>Code</SubType>
</Compile> </Compile>
<Compile Include="fa_test.py"> <Compile Include="fa_test.py">

View File

@ -20,7 +20,7 @@ def split_word(word, multi_character_phones):
Args: Args:
word (str): a word written in given phoneset. word (str): a word written in given phoneset.
multi_character_phones (list): the list of multicharacter phones which is considered as one phone. this can be obtained with phoneset definition such as fame_phoneset.py. multi_character_phones (list): the list of multicharacter phones which is considered as one phone. this can be obtained with phoneset definition such as fame_ipa.py.
Returns: Returns:
(word_seperated) (list): the word splitted in given phoneset. (word_seperated) (list): the word splitted in given phoneset.

127
acoustic_model/fame_asr.py Normal file
View File

@ -0,0 +1,127 @@
""" definition of the phones to be used. """
# phonese in {FAME}/lexicon/lex.asr
phoneset = [
# vowels
'a',
'a:',
'e',
'e:',
'i',
'i:',
'',
'o',
'o:',
'ö',
'ö:',
'u',
'u:',
'ü',
'ü:',
#'ú', # only appears in word 'feeste'(út) and 'gaste'(út) which are 'f e: s t ə' and 'yn' in lex_asr. The pronunciation in Fries may be mistakes so I removed this phone.
'',
'y',
'ɔ',
'ɔ:',
'ɔ̈',
'ɔ̈:',
'ə',
'ɛ',
'ɛ:',
'ɪ',
'ɪ:',
# plosives
'p',
'b',
't',
'd',
'k',
'g',
'ɡ', # = 'g'
# nasals
'm',
'n',
'ŋ',
# fricatives
'f',
'v',
's',
's:',
'z',
'x',
'h',
# tap and flip
'r',
'r:',
# approximant
'j',
'l'
]
## reduce the number of phones.
# the phones which seldom occur are replaced with another more popular phones.
# replacements are based on the advice from Martijn Wieling.
reduction_key = {
'y':'i:', 'e':'e:', 'ə:':'ɛ:', 'r:':'r', 'ɡ':'g'
}
# already removed beforehand in phoneset. Just to be sure.
phones_to_be_removed = ['ú', 's:', 'ɔ̈:']
phoneset_short = [reduction_key.get(i, i) for i in phoneset
if not i in phones_to_be_removed]
phoneset_short = list(set(phoneset_short))
phoneset_short.sort()
## translation_key to htk format (ascii).
# phones which gives UnicodeEncodeError when phone.encode("ascii")
# are replaced with other characters.
translation_key_asr2htk = {
'': 'i_',
'': 'u_',
# on the analogy of German umlaut, 'e' is used.
'ö': 'oe', 'ö:': 'oe:',
'ü': 'ue', 'ü:': 'ue:',
# on the analogy of Chinese...
'ŋ': 'ng',
# refer to Xsampa.
'ɔ': 'O', 'ɔ:': 'O:', 'ɔ̈': 'Oe',
'ɛ': 'E', 'ɛ:': 'E:',
'ɪ': 'I', 'ɪ:': 'I:',
# it is @ in Xsampa, but that is not handy on HTK.
'ə': 'A'
}
phoneset_htk = [translation_key_asr2htk.get(i, i) for i in phoneset_short]
## check
#for i in phoneset_short:
# try:
# print("{0} --> {1}".format(i, i.encode("ascii")))
# except UnicodeEncodeError:
# print(">>> {}".format(i))
## the list of multi character phones.
# for example, the length of 'a:' is 3, but in the codes it is treated as one letter.
# original.
multi_character_phones = [i for i in phoneset if len(i) > 1]
multi_character_phones.sort(key=len, reverse=True)
# phonset reduced.
multi_character_phones_short = [i for i in phoneset_short if len(i) > 1]
multi_character_phones_short.sort(key=len, reverse=True)
# htk compatible.
multi_character_phones_htk = [i for i in phoneset_htk if len(i) > 1]
multi_character_phones_htk.sort(key=len, reverse=True)

View File

@ -1,5 +1,4 @@
import os import os
os.chdir(r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model')
import sys import sys
from collections import Counter from collections import Counter
@ -9,7 +8,7 @@ import numpy as np
import pandas as pd import pandas as pd
import defaultfiles as default import defaultfiles as default
import fame_phoneset from phoneset import fame_ipa
import convert_phone_set import convert_phone_set
@ -110,14 +109,6 @@ import convert_phone_set
# return ipa # return ipa
#def make_filelist(input_dir, output_txt):
# """ Make a list of files in the input_dir. """
# filenames = os.listdir(input_dir)
# with open(output_txt, 'w') as fout:
# for filename in filenames:
# fout.write(input_dir + '\\' + filename + '\n')
#def make_htk_dict(word, pronvar_, fileDic, output_type): #def make_htk_dict(word, pronvar_, fileDic, output_type):
# """ # """
@ -179,10 +170,11 @@ def make_hcopy_scp_from_filelist_in_fame(fame_dir, dataset, feature_dir, hcopy_s
fout.write(wav_file + '\t' + mfc_file + '\n') fout.write(wav_file + '\t' + mfc_file + '\n')
return
def load_lexicon(lexicon_file): def load_lexicon(lexicon_file):
""" load lexicon file as Data Frame. """ load lexicon file as data frame.
Args: Args:
lexicon_file (path): lexicon in the format of 'word' /t 'pronunciation'. lexicon_file (path): lexicon in the format of 'word' /t 'pronunciation'.
@ -196,25 +188,27 @@ def load_lexicon(lexicon_file):
return lex return lex
def get_phoneset_from_lexicon(lexicon_file, phoneset='asr'): def get_phoneset_from_lexicon(lexicon_file, phoneset_name='asr'):
""" Make a list of phones which appears in the lexicon. """ Make a list of phones which appears in the lexicon.
Args: Args:
lexicon_file (path): lexicon in the format of 'word' /t 'pronunciation'. lexicon_file (path): lexicon in the format of 'word' /t 'pronunciation'.
phoneset (str): the phoneset with which lexicon_file is written. 'asr'(default) or 'ipa'. phoneset_name (str): the name of phoneset with which lexicon_file is written. 'asr'(default) or 'ipa'.
Returns: Returns:
(list_of_phones) (set): the set of phones included in the lexicon_file. (list_of_phones) (set): the set of phones included in the lexicon_file.
""" """
assert phoneset in ['asr', 'ipa'], 'phoneset should be \'asr\' or \'ipa\'' assert phoneset_name in ['asr', 'ipa'], 'phoneset_name should be \'asr\' or \'ipa\''
lex = load_lexicon(lexicon_file) lex = load_lexicon(lexicon_file)
if phoneset == 'asr': if phoneset_name == 'asr':
return set(' '.join(lex['pronunciation']).split(' ')) return set(' '.join(lex['pronunciation']).split(' '))
elif phoneset == 'ipa': elif phoneset_name == 'ipa':
join_pronunciations = ''.join(lex['pronunciation']) join_pronunciations = ''.join(lex['pronunciation'])
return set(convert_phone_set.split_word(join_pronunciations, fame_phoneset.multi_character_phones_ipa)) return set(convert_phone_set.split_word(join_pronunciations, fame_ipa.multi_character_phones))
return
def extract_unknown_phones(ipa, known_phones): def extract_unknown_phones(ipa, known_phones):
@ -228,7 +222,7 @@ def extract_unknown_phones(ipa, known_phones):
(list_of_phones) (list): unknown phones not included in 'known_phones'. (list_of_phones) (list): unknown phones not included in 'known_phones'.
""" """
ipa_split = convert_phone_set.split_word(ipa, fame_phoneset.multi_character_phones_ipa) ipa_split = convert_phone_set.split_word(ipa, fame_ipa.multi_character_phones)
return [i for i in ipa_split if not i in known_phones] return [i for i in ipa_split if not i in known_phones]
@ -247,14 +241,14 @@ def get_translation_key(lexicon_file_ipa, lexicon_file_asr):
""" """
lex_ipa = load_lexicon(lexicon_file_ipa) lex_ipa = load_lexicon(lexicon_file_ipa)
lex_asr = load_lexicon(lexicon_file_asr) lex_asr = load_lexicon(lexicon_file_asr)
phone_unknown = fame_phoneset.phoneset_ipa[:] phone_unknown = fame_ipa.phoneset[:]
translation_key = dict() translation_key = dict()
for word in lex_ipa['word']: for word in lex_ipa['word']:
if np.sum(lex_ipa['word'] == word) == 1 and np.sum(lex_asr['word'] == word) == 1: if np.sum(lex_ipa['word'] == word) == 1 and np.sum(lex_asr['word'] == word) == 1:
ipa = lex_ipa[lex_ipa['word'] == word].iat[0, 1] ipa = lex_ipa[lex_ipa['word'] == word].iat[0, 1]
asr = lex_asr[lex_asr['word'] == word].iat[0, 1] asr = lex_asr[lex_asr['word'] == word].iat[0, 1]
ipa_list = convert_phone_set.split_word(ipa, fame_phoneset.multi_character_phones_ipa) ipa_list = convert_phone_set.split_word(ipa, fame_ipa.multi_character_phones)
asr_list = asr.split(' ') asr_list = asr.split(' ')
# if there are phones which is not in phone_unknown # if there are phones which is not in phone_unknown
@ -268,13 +262,13 @@ def get_translation_key(lexicon_file_ipa, lexicon_file_asr):
return translation_key, list(phone_unknown) return translation_key, list(phone_unknown)
def find_phone(lexicon_file, phone, phoneset='ipa'): def find_phone(lexicon_file, phone, phoneset_name='ipa'):
""" extract rows where the phone is used in the lexicon_file. """ extract rows where the phone is used in the lexicon_file.
Args: Args:
lexicon_file (path): lexicon in the format of 'word' /t 'pronunciation'. lexicon_file (path): lexicon in the format of 'word' /t 'pronunciation'.
phone (str): the phone to be searched. phone (str): the phone to be searched.
phoneset (str): the phoneset with which lexicon_file is written. 'asr' or 'ipa'(default). phoneset_name (str): the name of phoneset_name with which lexicon_file is written. 'asr' or 'ipa'(default).
Returns: Returns:
extracted (df): rows where the phone is used. extracted (df): rows where the phone is used.
@ -283,7 +277,7 @@ def find_phone(lexicon_file, phone, phoneset='ipa'):
* develop when the phonset == 'asr'. * develop when the phonset == 'asr'.
""" """
assert phoneset in ['asr', 'ipa'], 'phoneset should be \'asr\' or \'ipa\'' assert phoneset_name in ['asr', 'ipa'], 'phoneset_name should be \'asr\' or \'ipa\''
lex = load_lexicon(lexicon_file) lex = load_lexicon(lexicon_file)
@ -292,8 +286,8 @@ def find_phone(lexicon_file, phone, phoneset='ipa'):
extracted = pd.DataFrame(index=[], columns=['word', 'pronunciation']) extracted = pd.DataFrame(index=[], columns=['word', 'pronunciation'])
for index, row in lex_.iterrows(): for index, row in lex_.iterrows():
if phoneset == 'ipa': if phoneset_name == 'ipa':
pronunciation = convert_phone_set.split_word(row['pronunciation'], fame_phoneset.multi_character_phones_ipa) pronunciation = convert_phone_set.split_word(row['pronunciation'], fame_ipa.multi_character_phones)
if phone in pronunciation: if phone in pronunciation:
extracted_ = pd.Series([row['word'], pronunciation], index=extracted.columns) extracted_ = pd.Series([row['word'], pronunciation], index=extracted.columns)
extracted = extracted.append(extracted_, ignore_index=True) extracted = extracted.append(extracted_, ignore_index=True)

View File

@ -8,8 +8,8 @@ import tempfile
#from collections import Counter #from collections import Counter
import time import time
#import numpy as np import numpy as np
#import pandas as pd import pandas as pd
import fame_functions import fame_functions
import defaultfiles as default import defaultfiles as default
@ -54,6 +54,10 @@ conv_lexicon = 1
#mkhmmdefs_pl = config['Settings']['mkhmmdefs_pl'] #mkhmmdefs_pl = config['Settings']['mkhmmdefs_pl']
#FAME_dir = config['Settings']['FAME_dir'] #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 = FAME_dir + '\\lexicon\\lex.asr'
#lex_asr_htk = FAME_dir + '\\lexicon\\lex.asr_htk' #lex_asr_htk = FAME_dir + '\\lexicon\\lex.asr_htk'
#lex_oov = FAME_dir + '\\lexicon\\lex.oov' #lex_oov = FAME_dir + '\\lexicon\\lex.oov'
@ -111,71 +115,6 @@ if extract_features:
## ======================= convert lexicon from ipa to fame_htk ======================= ## ======================= convert lexicon from ipa to fame_htk =======================
if conv_lexicon: if conv_lexicon:
print('==== convert lexicon from ipa 2 fame ====\n') print('==== convert lexicon from ipa 2 fame ====\n')
#dir_out = r'c:\Users\Aki\source\repos\acoustic_model\_tmp'
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')
# get the correspondence between lex_ipa and lex_asr.
lex_asr = fame_functions.load_lexicon(lexicon_asr)
lex_ipa = fame_functions.load_lexicon(lexicon_ipa)
if 1:
timer_start = time.time()
translation_key, phone_unknown = fame_functions.get_translation_key(lexicon_ipa, lexicon_asr)
print("elapsed time: {}".format(time.time() - timer_start))
np.save('translation_key_ipa2asr.npy', translation_key)
np.save('phone_unknown.npy', phone_unknown)
else:
translation_key = np.load('translation_key_ipa2asr.npy').item()
phone_unknown = np.load('phone_unknown.npy')
phone_unknown = list(phone_unknown)
## manually check the correspondence for the phone in phone_unknown.
#p = phone_unknown[0]
#lex_ipa_ = find_phone(lexicon_ipa, p, phoneset='ipa')
#for word in lex_ipa_['word']:
# ipa = lex_ipa[lex_ipa['word'] == word].iat[0, 1]
# if np.sum(lex_asr['word'] == word) > 0:
# asr = lex_asr[lex_asr['word'] == word].iat[0, 1]
# ipa_list = convert_phone_set.split_word(ipa, fame_phoneset.multi_character_phones_ipa)
# asr_list = asr.split(' ')
# if p in ipa_list and (len(ipa_list) == len(asr_list)):
# print("{0}: {1} --> {2}".format(word, ipa_list, asr_list))
# for ipa_, asr_ in zip(ipa_list, asr_list):
# if ipa_ in phone_unknown:
# translation_key[ipa_] = asr_
# phone_unknown.remove(ipa_)
## check if all the phones in lexicon_ipa are in fame_phoneset.py.
#timer_start = time.time()
#phoneset_lex = get_phoneset_from_lexicon(lexicon_ipa, phoneset='ipa')
#print("elapsed time: {}".format(time.time() - timer_start))
#phoneset_py = fame_phoneset.phoneset_ipa
#set(phoneset_lex) - set(phoneset_py)
##timer_start = time.time()
##extracted = find_phone(lexicon_ipa, 'ⁿ')
##print("elapsed time: {}".format(time.time() - timer_start))
# lex.asr is Kaldi compatible version of lex.ipa.
# to check...
#lexicon_ipa = pd.read_table(lex_ipa, names=['word', 'pronunciation'])
#with open(lex_ipa_, "w", encoding="utf-8") as fout:
# for word, pronunciation in zip(lexicon_ipa['word'], lexicon_ipa['pronunciation']):
# # ignore nasalization and '.'
# pronunciation_ = pronunciation.replace(u'ⁿ', '')
# pronunciation_ = pronunciation_.replace('.', '')
# pronunciation_split = convert_phone_set.split_ipa_fame(pronunciation_)
# fout.write("{0}\t{1}\n".format(word, ' '.join(pronunciation_split)))
# convert each lexicon from ipa description to fame_htk phoneset. # convert each lexicon from ipa description to fame_htk phoneset.
#am_func.ipa2famehtk_lexicon(lex_oov, lex_oov_htk) #am_func.ipa2famehtk_lexicon(lex_oov, lex_oov_htk)
#am_func.ipa2famehtk_lexicon(lex_asr, lex_asr_htk) #am_func.ipa2famehtk_lexicon(lex_asr, lex_asr_htk)

107
acoustic_model/fame_ipa.py Normal file
View File

@ -0,0 +1,107 @@
""" definition of the phones to be used. """
phoneset = [
# vowels
'',
'i̯ⁿ',
'y',
'i',
'i.',
'iⁿ',
'i:',
'i:ⁿ',
'ɪ',
'ɪⁿ',
'ɪ.',
#'ɪ:', # not included in lex.ipa
'ɪ:ⁿ',
'e',
'e:',
'e:ⁿ',
'ə',
'əⁿ',
'ə:',
'ɛ',
'ɛ.',
'ɛⁿ',
'ɛ:',
'ɛ:ⁿ',
'a',
'aⁿ',
'a.',
'a:',
'a:ⁿ',
'',
'ṷ.',
'ṷⁿ',
#'ú', # only appears in word 'feeste'(út) and 'gaste'(út) which are 'f e: s t ə' and 'yn' in lex_asr. The pronunciation in Fries may be mistakes so I removed this phone.
'u',
'uⁿ',
'u.',
'u:',
'u:ⁿ',
'ü',
'ü.',
'üⁿ',
'ü:',
'ü:ⁿ',
'o',
'oⁿ',
'o.',
'o:',
'o:ⁿ',
'ö',
'ö.',
'öⁿ',
'ö:',
'ö:ⁿ',
'ɔ',
'ɔ.',
'ɔⁿ',
'ɔ:',
'ɔ:ⁿ',
#'ɔ̈', # not included in lex.ipa
'ɔ̈.',
'ɔ̈:',
# plosives
'p',
'b',
't',
'tⁿ',
'd',
'k',
'g',
'ɡ', # = 'g'
# nasals
'm',
'n',
'ŋ',
# fricatives
'f',
'v',
's',
's:',
'z',
'zⁿ',
'x',
'h',
# tap and flip
'r',
'r.', # only appears in word 'mearpartijestelsel'(does not exist in lex_asr) and 'tenoarpartij'.
'r:', # only appears in word 'mûsearflearmûs' and 'sjochdêr'.
# approximant
'j',
'j.',
'l'
]
## the list of multi character phones.
# for example, the length of 'i̯ⁿ' is 3, but in the codes it is treated as one letter.
multi_character_phones = [i for i in phoneset if len(i) > 1]
multi_character_phones.sort(key=len, reverse=True)

View File

@ -0,0 +1,93 @@
import sys
import os
os.chdir(r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model')
import time
import numpy as np
import pandas as pd
import fame_functions
import defaultfiles as default
sys.path.append(default.toolbox_dir)
from phoneset import fame_ipa, fame_asr
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')
## check if all the phones in lexicon.ipa are in fame_ipa.py.
#timer_start = time.time()
#phoneset_lex = fame_functions.get_phoneset_from_lexicon(lexicon_ipa, phoneset='ipa')
#phoneset_py = fame_ipa.phoneset
#print("phones which is in lexicon.ipa but not in fame_ipa.py:\n{}".format(
# set(phoneset_lex) - set(phoneset_py)))
#print("elapsed time: {}".format(time.time() - timer_start))
# check which word has the phone.
#timer_start = time.time()
#extracted = find_phone(lexicon_ipa, 'ⁿ')
#print("elapsed time: {}".format(time.time() - timer_start))
## get the correspondence between lex_ipa and lex_asr.
lex_asr = fame_functions.load_lexicon(lexicon_asr)
lex_ipa = fame_functions.load_lexicon(lexicon_ipa)
if 0:
timer_start = time.time()
translation_key_ipa2asr, phone_unknown = fame_functions.get_translation_key(lexicon_ipa, lexicon_asr)
print("elapsed time: {}".format(time.time() - timer_start))
np.save(os.path.join('phoneset', 'output_get_translation_key_translation_key.npy'), translation_key_ipa2asr)
np.save(os.path.join('phoneset', 'output_get_translation_key_phone_unknown.npy'), phone_unknown)
else:
translation_key_ipa2asr = np.load(os.path.join('phoneset', 'output_get_translation_key_translation_key.npy')).item()
phone_unknown = np.load(os.path.join('phoneset', 'output_get_translation_key_phone_unknown.npy'))
phone_unknown = list(phone_unknown)
# manually check the correspondence for the phone in phone_unknown.
#p = phone_unknown[0]
#lex_ipa_ = find_phone(lexicon_ipa, p, phoneset='ipa')
#for word in lex_ipa_['word']:
# ipa = lex_ipa[lex_ipa['word'] == word].iat[0, 1]
# if np.sum(lex_asr['word'] == word) > 0:
# asr = lex_asr[lex_asr['word'] == word].iat[0, 1]
# ipa_list = convert_phone_set.split_word(ipa, fame_ipa.multi_character_phones)
# asr_list = asr.split(' ')
# if p in ipa_list and (len(ipa_list) == len(asr_list)):
# print("{0}: {1} --> {2}".format(word, ipa_list, asr_list))
# for ipa_, asr_ in zip(ipa_list, asr_list):
# if ipa_ in phone_unknown:
# translation_key_ipa2asr[ipa_] = asr_
# phone_unknown.remove(ipa_)
translation_key_ipa2asr['ə:'] = 'ə'
translation_key_ipa2asr['r.'] = 'r'
translation_key_ipa2asr['r:'] = 'r'
np.save(os.path.join('phoneset', 'fame_ipa2asr.npy'), translation_key_ipa2asr)
## check if all the phones in lexicon.asr are in translation_key_ipa2asr.
timer_start = time.time()
phoneset_lex = fame_functions.get_phoneset_from_lexicon(lexicon_asr, phoneset='asr')
phoneset_lex.remove("")
phoneset_asr = list(set(translation_key_ipa2asr.values()))
print("phones which is in lexicon.asr but not in the translation_key_ipa2asr:\n{}".format(
set(phoneset_lex) - set(phoneset_asr)))
print("elapsed time: {}".format(time.time() - timer_start))
## make the translation key between asr to htk.
#multi_character_phones = [i for i in phoneset_asr if len(i) > 1]
#multi_character_phones.sort(key=len, reverse=True)
#lexicon_ipa = pd.read_table(lex_ipa, names=['word', 'pronunciation'])
#with open(lex_ipa_, "w", encoding="utf-8") as fout:
# for word, pronunciation in zip(lexicon_ipa['word'], lexicon_ipa['pronunciation']):
# # ignore nasalization and '.'
# pronunciation_ = pronunciation.replace(u'ⁿ', '')
# pronunciation_ = pronunciation_.replace('.', '')
# pronunciation_split = convert_phone_set.split_ipa_fame(pronunciation_)
# fout.write("{0}\t{1}\n".format(word, ' '.join(pronunciation_split)))

View File

@ -1,7 +1,6 @@
""" definition of the phones to be used. """ """ definition of the phones to be used. """
## phones in IPA. phoneset = [
phoneset_ipa = [
# vowels # vowels
'', '',
'i̯ⁿ', 'i̯ⁿ',
@ -103,5 +102,5 @@ phoneset_ipa = [
## the list of multi character phones. ## the list of multi character phones.
# for example, the length of 'i̯ⁿ' is 3, but in the codes it is treated as one letter. # for example, the length of 'i̯ⁿ' is 3, but in the codes it is treated as one letter.
multi_character_phones_ipa = [i for i in phoneset_ipa if len(i) > 1] multi_character_phones = [i for i in phoneset if len(i) > 1]
multi_character_phones_ipa.sort(key=len, reverse=True) multi_character_phones.sort(key=len, reverse=True)

View File

@ -0,0 +1,106 @@
""" definition of the phones to be used. """
phoneset = [
# vowels
'',
'i̯ⁿ',
'y',
'i',
'i.',
'iⁿ',
'i:',
'i:ⁿ',
'ɪ',
'ɪⁿ',
'ɪ.',
#'ɪ:', # not included in lex.ipa
'ɪ:ⁿ',
'e',
'e:',
'e:ⁿ',
'ə',
'əⁿ',
'ə:',
'ɛ',
'ɛ.',
'ɛⁿ',
'ɛ:',
'ɛ:ⁿ',
'a',
'aⁿ',
'a.',
'a:',
'a:ⁿ',
'',
'ṷ.',
'ṷⁿ',
#'ú', # only appears in word 'feeste'(út) and 'gaste'(út) which are 'f e: s t ə' and 'yn' in lex_asr.
'u',
'uⁿ',
'u.',
'u:',
'u:ⁿ',
'ü',
'ü.',
'üⁿ',
'ü:',
'ü:ⁿ',
'o',
'oⁿ',
'o.',
'o:',
'o:ⁿ',
'ö',
'ö.',
'öⁿ',
'ö:',
'ö:ⁿ',
'ɔ',
'ɔ.',
'ɔⁿ',
'ɔ:',
'ɔ:ⁿ',
#'ɔ̈', # not included in lex.ipa
'ɔ̈.',
'ɔ̈:',
# plosives
'p',
'b',
't',
'tⁿ',
'd',
'k',
'g',
'ɡ', # = 'g'
# nasals
'm',
'n',
'ŋ',
# fricatives
'f',
'v',
's',
's:',
'z',
'zⁿ',
'x',
'h',
# tap and flip
'r',
'r.', # only appears in word 'mearpartijestelsel'(does not exist in lex_asr) and 'tenoarpartij'.
'r:', # only appears in word 'mûsearflearmûs' and 'sjochdêr'.
# approximant
'j',
'j.',
'l'
]
## the list of multi character phones.
# for example, the length of 'i̯ⁿ' is 3, but in the codes it is treated as one letter.
multi_character_phones = [i for i in phoneset if len(i) > 1]
multi_character_phones.sort(key=len, reverse=True)

Binary file not shown.