Browse Source
fame_asr phoneset is added including reduced version and htk compatible version.
master
fame_asr phoneset is added including reduced version and htk compatible version.
master
yemaozi88
3 years ago
14 changed files with 465 additions and 98 deletions
-
BIN.vs/acoustic_model/v15/.suo
-
BINacoustic_model/__pycache__/defaultfiles.cpython-36.pyc
-
4acoustic_model/acoustic_model.pyproj
-
2acoustic_model/convert_phone_set.py
-
127acoustic_model/fame_asr.py
-
44acoustic_model/fame_functions.py
-
73acoustic_model/fame_hmm.py
-
107acoustic_model/fame_ipa.py
-
93acoustic_model/fame_test.py
-
7acoustic_model/phoneset/fame_asr.py
-
106acoustic_model/phoneset/fame_ipa.py
-
BINacoustic_model/phoneset/fame_ipa2asr.npy
-
BINacoustic_model/phoneset/output_get_translation_key_phone_unknown.npy
-
BINacoustic_model/phoneset/output_get_translation_key_translation_key.npy
@ -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:', |
|||
'i̯', |
|||
'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. |
|||
'ṷ', |
|||
'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 = { |
|||
'i̯': 'i_', |
|||
'ṷ': '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) |
|||
@ -0,0 +1,107 @@ |
|||
""" definition of the phones to be used. """ |
|||
|
|||
phoneset = [ |
|||
# vowels |
|||
'i̯', |
|||
'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', |
|||
'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) |
|||
@ -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))) |
|||
@ -0,0 +1,106 @@ |
|||
""" definition of the phones to be used. """ |
|||
|
|||
phoneset = [ |
|||
# vowels |
|||
'i̯', |
|||
'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', |
|||
'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) |
|||
Write
Preview
Loading…
Cancel
Save
Reference in new issue