dataset for experiments in check_novoapi is updated.

This commit is contained in:
yemaozi88 2019-04-22 02:03:50 +02:00
parent 2004399179
commit 97486e5599
6 changed files with 90 additions and 58 deletions

Binary file not shown.

View File

@ -4,7 +4,7 @@
<SchemaVersion>2.0</SchemaVersion> <SchemaVersion>2.0</SchemaVersion>
<ProjectGuid>4d8c8573-32f0-4a62-9e62-3ce5cc680390</ProjectGuid> <ProjectGuid>4d8c8573-32f0-4a62-9e62-3ce5cc680390</ProjectGuid>
<ProjectHome>.</ProjectHome> <ProjectHome>.</ProjectHome>
<StartupFile>fame_hmm.py</StartupFile> <StartupFile>check_novoapi.py</StartupFile>
<SearchPath> <SearchPath>
</SearchPath> </SearchPath>
<WorkingDirectory>.</WorkingDirectory> <WorkingDirectory>.</WorkingDirectory>

View File

@ -29,48 +29,47 @@ forced_alignment_novo70 = True
## ===== load novo phoneset ===== ## ===== load novo phoneset =====
phoneset_ipa, phoneset_novo70, translation_key_ipa2novo70, translation_key_novo702ipa = novoapi_functions.load_phonset() phoneset_ipa, phoneset_novo70, translation_key_ipa2novo70, translation_key_novo702ipa = novoapi_functions.load_novo70_phoneset()
## ===== extract pronunciations written in novo70 only (not_in_novo70) ===== ## ===== extract pronunciations written in novo70 only (not_in_novo70) =====
# As per Nederlandse phoneset_aki.xlsx recieved from David
# [ɔː] oh / ohr
# [ɪː] ih / ihr
# [iː] iy
# [œː] uh
# [ɛː] eh
# [w] wv in IPA written as ʋ.
david_suggestion = ['ɔː', 'ɪː', 'iː', 'œː', 'ɛː', 'w']
## read pronunciation variants. ## read pronunciation variants.
stimmen_transcription_ = pd.ExcelFile(default.stimmen_transcription_xlsx) #stimmen_transcription_ = pd.ExcelFile(default.stimmen_transcription_xlsx)
df = pd.read_excel(stimmen_transcription_, 'frequency') #df = pd.read_excel(stimmen_transcription_, 'frequency')
transcription_ipa = list(df['IPA']) #transcription_ipa = list(df['IPA'])
# transcription mistake?
transcription_ipa = [ipa.replace(';', 'ː') for ipa in transcription_ipa if not ipa=='pypɪl' and not pd.isnull(ipa)]
transcription_ipa = [ipa.replace('ˑ', '') for ipa in transcription_ipa] # only one case.
not_in_novo70 = [] stimmen_test_dir = r'c:\OneDrive\Research\rug\_data\stimmen_test'
all_in_novo70 = [] df = stimmen_functions.load_transcriptions_novo70(stimmen_test_dir)
for ipa in transcription_ipa:
ipa = ipa.replace(':', 'ː')
ipa = convert_phone_set.split_ipa(ipa)
# list of phones not in novo70 phoneset.
not_in_novo70_ = [phone for phone in ipa
if not phone in phoneset_ipa and not phone in david_suggestion]
not_in_novo70_ = [phone.replace('sp', '') for phone in not_in_novo70_]
not_in_novo70_ = [phone.replace(':', '') for phone in not_in_novo70_]
not_in_novo70_ = [phone.replace('ː', '') for phone in not_in_novo70_]
if len(not_in_novo70_) == 0:
all_in_novo70.append(''.join(ipa))
#translation_key.get(phone, phone) ## transcription mistake?
not_in_novo70.extend(not_in_novo70_) #transcription_ipa = [ipa.replace(';', 'ː') for ipa in transcription_ipa if not ipa=='pypɪl' and not pd.isnull(ipa)]
not_in_novo70_list = list(set(not_in_novo70)) #transcription_ipa = [ipa.replace('ˑ', '') for ipa in transcription_ipa] # only one case.
#not_in_novo70 = []
#all_in_novo70 = []
#for ipa in transcription_ipa:
# ipa = ipa.replace(':', 'ː')
# ipa = convert_phone_set.split_ipa(ipa)
# # list of phones not in novo70 phoneset.
# not_in_novo70_ = [phone for phone in ipa
# if not phone in phoneset_ipa and not phone in david_suggestion]
# not_in_novo70_ = [phone.replace('sp', '') for phone in not_in_novo70_]
# not_in_novo70_ = [phone.replace(':', '') for phone in not_in_novo70_]
# not_in_novo70_ = [phone.replace('ː', '') for phone in not_in_novo70_]
# if len(not_in_novo70_) == 0:
# all_in_novo70.append(''.join(ipa))
# #translation_key.get(phone, phone)
# not_in_novo70.extend(not_in_novo70_)
#not_in_novo70_list = list(set(not_in_novo70))
## check which phones used in stimmen but not in novo70 ## check which phones used in stimmen but not in novo70
@ -85,41 +84,43 @@ not_in_novo70_list = list(set(not_in_novo70))
# [ʊ] 'ʊ'(1) --> can be ʏ (uh)?? # [ʊ] 'ʊ'(1) --> can be ʏ (uh)??
# [χ] --> can be x?? # [χ] --> can be x??
def search_phone_ipa(x, phone_list): #def search_phone_ipa(x, phone_list):
x_in_item = [] # x_in_item = []
for ipa in phone_list: # for ipa in phone_list:
ipa_original = ipa # ipa_original = ipa
ipa = ipa.replace(':', 'ː') # ipa = ipa.replace(':', 'ː')
ipa = convert_phone_set.split_ipa(ipa) # ipa = convert_phone_set.split_ipa(ipa)
if x in ipa and not x+':' in ipa: # if x in ipa and not x+':' in ipa:
x_in_item.append(ipa_original) # x_in_item.append(ipa_original)
return x_in_item # return x_in_item
#search_phone_ipa('ø', transcription_ipa) #search_phone_ipa('ø', transcription_ipa)
## ===== load all transcriptions (df) ===== ## ===== load all transcriptions (df) =====
df = stimmen_functions.load_transcriptions() #df = stimmen_functions.load_transcriptions()
word_list = [i for i in list(set(df['word'])) if not pd.isnull(i)] word_list = [i for i in list(set(df['word'])) if not pd.isnull(i)]
word_list = sorted(word_list) word_list = sorted(word_list)
## check frequency of each pronunciation variants ## check frequency of each pronunciation variants
cols = ['word', 'ipa', 'frequency'] #cols = ['word', 'ipa', 'frequency']
df_samples = pd.DataFrame(index=[], columns=cols) #df_samples = pd.DataFrame(index=[], columns=cols)
for ipa in all_in_novo70: #for ipa in all_in_novo70:
ipa = ipa.replace('ː', ':') # ipa = ipa.replace('ː', ':')
samples = df[df['ipa'] == ipa] # samples = df[df['ipa'] == ipa]
word = list(set(samples['word']))[0] # word = list(set(samples['word']))[0]
samples_Series = pd.Series([word, ipa, len(samples)], index=df_samples.columns) # samples_Series = pd.Series([word, ipa, len(samples)], index=df_samples.columns)
df_samples = df_samples.append(samples_Series, ignore_index=True) # df_samples = df_samples.append(samples_Series, ignore_index=True)
# each word # each word
df_per_word = pd.DataFrame(index=[], columns=df_samples.keys()) #df_per_word = pd.DataFrame(index=[], columns=df_samples.keys())
for word in word_list: #for word in word_list:
df_samples_ = df_samples[df_samples['word']==word] word = word_list[2]
df_samples_ = df_samples_[df_samples_['frequency']>2] df_ = df[df['word']==word]
df_per_word = df_per_word.append(df_samples_, ignore_index=True) np.unique(list(df_['ipa']))
#df_samples_ = df_samples_[df_samples_['frequency']>2]
#df_per_word = df_per_word.append(df_samples_, ignore_index=True)
#df_per_word.to_excel(os.path.join(default.stimmen_dir, 'pronunciation_variants_novo70.xlsx'), encoding="utf-8") #df_per_word.to_excel(os.path.join(default.stimmen_dir, 'pronunciation_variants_novo70.xlsx'), encoding="utf-8")

View File

@ -352,9 +352,6 @@ def fix_lexicon(lexicon_file):
return return
#def add_sp_to_lexicon(lexicon_file):
def word2htk(word): def word2htk(word):
return ''.join([fame_asr.translation_key_word2htk.get(i, i) for i in word]) return ''.join([fame_asr.translation_key_word2htk.get(i, i) for i in word])

View File

@ -174,6 +174,8 @@ def forced_alignment(wav_file, word, pronunciation_ipa):
p.add_argument("--user", default='martijn.wieling') p.add_argument("--user", default='martijn.wieling')
p.add_argument("--password", default='xxxxxx') p.add_argument("--password", default='xxxxxx')
args = p.parse_args() args = p.parse_args()
rec = session.Recognizer(grammar_version="1.0", lang="nl", snodeid=101, user=args.user, password=args.password, keepopen=True) # , modeldir=modeldir) rec = session.Recognizer(grammar_version="1.0", lang="nl", snodeid=101, user=args.user, password=args.password, keepopen=True) # , modeldir=modeldir)
@ -194,6 +196,24 @@ def result2pronunciation(result, word):
return pronunciation_ipa, pronunciation_novo70, llh return pronunciation_ipa, pronunciation_novo70, llh
def phones_not_in_novo70(ipa):
""" extract phones which is not in novo70 phoneset. """
phoneset_ipa, _, _, _ = load_novo70_phoneset()
# As per Nederlandse phoneset_aki.xlsx recieved from David
# [ɔː] oh / ohr
# [ɪː] ih / ihr
# [iː] iy
# [œː] uh
# [ɛː] eh
# [w] wv in IPA written as ʋ.
david_suggestion = ['ɔː', 'ɪː', 'iː', 'œː', 'ɛː', 'w']
return [phone for phone in split_ipa(ipa)
if not phone in phoneset_ipa and not phone in david_suggestion]
if __name__ == 'main': if __name__ == 'main':
pronunciation_ipa = ['rø:s', 'mɑn', 'mɑntsjə'] pronunciation_ipa = ['rø:s', 'mɑn', 'mɑntsjə']
#grammar = make_grammar('reus', pronunciation_ipa) #grammar = make_grammar('reus', pronunciation_ipa)

View File

@ -7,6 +7,7 @@ import pandas as pd
import convert_xsampa2ipa import convert_xsampa2ipa
import defaultfiles as default import defaultfiles as default
import fame_functions import fame_functions
import novoapi_functions
def _load_transcriptions(): def _load_transcriptions():
@ -67,6 +68,19 @@ def load_transcriptions_clean(clean_wav_dir):
return df_clean return df_clean
def load_transcriptions_novo70(clean_wav_dir):
""" extract rows of which ipa is written in novo70 phonset. """
df = load_transcriptions_clean(clean_wav_dir)
df_novo70 = pd.DataFrame(index=[], columns=list(df.keys()))
for index, row in df.iterrows():
not_in_novo70 = novoapi_functions.phones_not_in_novo70(row['ipa'])
if len(not_in_novo70) == 0:
df_novo70 = df_novo70.append(row, ignore_index=True)
return df_novo70
def add_row_htk(df): def add_row_htk(df):
""" df['htk'] is made from df['ipa'] and added. """ """ df['htk'] is made from df['ipa'] and added. """
htk = [] htk = []