Compare commits

..

3 Commits

9 changed files with 369 additions and 33 deletions

Binary file not shown.

View File

@ -35,9 +35,15 @@
<Compile Include="fa_test.py">
<SubType>Code</SubType>
</Compile>
<Compile Include="novoapi_forced_alignment.py">
<SubType>Code</SubType>
</Compile>
<Compile Include="htk_vs_kaldi.py">
<SubType>Code</SubType>
</Compile>
<Compile Include="novoapi_functions.py">
<SubType>Code</SubType>
</Compile>
</ItemGroup>
<ItemGroup>
<Content Include="config.ini" />

View File

@ -16,47 +16,121 @@ import acoustic_model_functions as am_func
import convert_xsampa2ipa
import defaultfiles as default
from forced_alignment import pyhtk
from forced_alignment import pyhtk, convert_phone_set
import novoapi
import novoapi_functions
## ======================= novo phoneset ======================
translation_key = dict()
phoneset_ipa, phoneset_novo70, translation_key = novoapi_functions.load_phonset()
#phonelist_novo70_ = pd.ExcelFile(default.phonelist_novo70_xlsx)
#df = pd.read_excel(phonelist_novo70_, 'list')
## *_simple includes columns which has only one phone in.
#for ipa, novo70 in zip(df['IPA_simple'], df['novo70_simple']):
# if not pd.isnull(ipa):
# print('{0}:{1}'.format(ipa, novo70))
# translation_key[ipa] = novo70
#phonelist_novo70 = np.unique(list(df['novo70_simple']))
phoneset_ipa = []
phoneset_novo70 = []
with open(default.cmu69_phoneset, "rt", encoding="utf-8") as fin:
lines = fin.read()
lines = lines.split('\n')
for line in lines:
words = line.split('\t')
if len(words) > 1:
novo70 = words[0]
ipa = words[1]
phoneset_ipa.append(ipa)
phoneset_novo70.append(novo70)
translation_key[ipa] = novo70
phoneset_ipa = np.unique(phoneset_ipa)
phoneset_novo70 = np.unique(phoneset_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']
## ======================= convert phones ======================
## ======================= extract words which is written only with novo70 ======================
mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', default.ipa_xsampa_converter_dir)
stimmen_transcription_ = pd.ExcelFile(default.stimmen_transcription_xlsx)
df = pd.read_excel(stimmen_transcription_, 'check')
df = pd.read_excel(stimmen_transcription_, '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))
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 = []
all_in_novo70 = []
for ipa in transcription_ipa:
ipa = ipa.replace(':', 'ː')
ipa = convert_phone_set.split_ipa(ipa)
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 phone is used in stimmen but not in novo70
# 'ʀ', 'ʁ',
# 'ɒ', 'ɐ',
# 'o', 'a' (o:, a:?)
# [e] 'nyːver mɑntsjə' (1)
# [ɾ] 'ɪːɾ'(1)
# [ɹ] 'iːjəɹ' (1), 'ɪ:ɹ' (1)
# [ø] 'gʀøtəpi:r'(1), 'grøtəpi:r'(1)
# [æ] 'røːzəʀæt'(2), 'røːzəræt'(1)
# [ʊ] 'ʊ'(1) --> can be ʏ (uh)??
# [χ] --> can be x??
def search_phone_ipa(x, phone_list):
x_in_item = []
for ipa in phone_list:
ipa_original = ipa
ipa = ipa.replace(':', 'ː')
ipa = convert_phone_set.split_ipa(ipa)
if x in ipa and not x+':' in ipa:
x_in_item.append(ipa_original)
return x_in_item
#search_phone_ipa('ø', transcription_ipa)
df = pd.read_excel(stimmen_transcription_, 'original')
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)
else:
ipas.append('')
# extract interesting cols.
df = pd.DataFrame({'filename': df['Filename'],
'word': df['Word'],
'xsampa': df['Self Xsampa'],
'ipa': pd.Series(ipas)})
# find options which all phones are in novo70.
#word_list = list(set(df['word']))
#word_list = [word for word in word_list if not pd.isnull(word)]
#word = word_list[1]
## pronunciation variants of 'word'
#df_ = df[df['word'] == word]['xsampa']
##pronunciation_variant = list(set(df_))
cols = ['word', 'ipa', 'frequency']
df_samples = pd.DataFrame(index=[], columns=cols)
for ipa in all_in_novo70:
ipa = ipa.replace('ː', ':')
samples = df[df['ipa'] == ipa]
word = list(set(samples['word']))[0]
samples_Series = pd.Series([word, ipa, len(samples)], index=df_samples.columns)
df_samples = df_samples.append(samples_Series, ignore_index=True)

View File

@ -42,4 +42,4 @@ phonelist_friesian_txt = os.path.join(experiments_dir, 'friesian', 'acoustic
novo_api_dir = os.path.join(WSL_dir, 'python-novo-api', 'novoapi')
#novo_api_dir = r'c:\Python36-32\Lib\site-packages\novoapi'
cmu69_phoneset = os.path.join(novo_api_dir, 'asr', 'phoneset', 'en', 'cmu69.phoneset')
novo70_phoneset = os.path.join(novo_api_dir, 'asr', 'phoneset', 'nl', 'novo70.phoneset')

View File

@ -0,0 +1,118 @@
#
# forced alignment using novo-api.
#
# *** IMPORTANT ***
# This file should be treated as confidencial.
# This file should not be copied or uploaded to public sites.
#
# NOTES:
# The usage of novo api: https://bitbucket.org/novolanguage/python-novo-api
# I couldn't make it work as I described in the mail to Martijn Bartelds on
# 2018/12/03.
# As per the advice from him, I modified testgrammer.py and made it a function.
#
# In order to run on Python 3.6, the following points are changed in novo-api.
# (1) backend/__init__.py
# - #import session
# from . import session
# (2) backend/session.py
# - #except Exception, e:
# except Exception as e:
# - #print self.last_message
# print(self.last_message)
# (3) asr/segment/praat.py
# - def print_tier(output, title, begin, end, segs, (format, formatter))
# def print_tier(output, title, begin, end, segs, format, formatter):
# (4) asr/spraaklab/__init.py
# - #import session
# from . import session
# (5) asr/spraaklab/schema.py
# - #print data, "validated not OK", e.message
# print("{0} validated not OK {1}".format(data, e.message))
# - #print data, "validated OK"
# print("{} validated OK".format(data))
# - #if isinstance(object, basestring):
# if isinstance(object, str)
#
# Aki Kunikoshi
# 428968@gmail.com
#
import argparse
import json
from novoapi.backend import session
import novoapi_functions
# username / password cannot be passed as artuments...
p = argparse.ArgumentParser()
#p.add_argument("--user", default=None)
#p.add_argument("--password", default=None)
p.add_argument("--user", default='martijn.wieling')
p.add_argument("--password", default='fa0Thaic')
args = p.parse_args()
wav_file = 'c:\\OneDrive\\WSL\\test\\onetwothree.wav'
rec = session.Recognizer(grammar_version="1.0", lang="nl", snodeid=101, user=args.user, password=args.password, keepopen=True) # , modeldir=modeldir)
grammar = {
"type": "confusion_network",
"version": "1.0",
"data": {
"kind": "sequence",
"elements": [{
"kind": "word",
"pronunciation": [{
"phones": ["wv",
"a1",
"n"],
"id": 0
},
{
"phones": ["wv",
"uh1",
"n"],
"id": 1
}],
"label": "one"
},
{
"kind": "word",
"pronunciation": [{
"phones": ["t",
"uw1"],
"id": 0
}],
"label": "two"
},
{
"kind": "word",
"pronunciation": [{
"phones": ["t",
"r",
"iy1"],
"id": 0
},
{
"phones": ["s",
"r",
"iy1"],
"id": 1
}],
"label": "three"
}]
},
"return_objects": ["grammar"],
"phoneset": "novo70"
}
res = rec.setgrammar(grammar)
#print "Set grammar result", res
#res = rec.recognize_wav("test/onetwothree.wav")
res = rec.recognize_wav(wav_file)
#print "Recognition result:", json.dumps(res.export(), indent=4)
# list of the pronunciation for each words
word = 'pauw'
pronunciation_ipa = ['pau', 'pɑu']
grammar = novoapi_functions.make_grammar(word, pronunciation_ipa)

View File

@ -0,0 +1,138 @@
import numpy as np
import defaultfiles as default
def load_phonset():
translation_key_ipa2novo70 = dict()
translation_key_novo702ipa = dict()
#phonelist_novo70_ = pd.ExcelFile(default.phonelist_novo70_xlsx)
#df = pd.read_excel(phonelist_novo70_, 'list')
## *_simple includes columns which has only one phone in.
#for ipa, novo70 in zip(df['IPA_simple'], df['novo70_simple']):
# if not pd.isnull(ipa):
# print('{0}:{1}'.format(ipa, novo70))
# translation_key[ipa] = novo70
#phonelist_novo70 = np.unique(list(df['novo70_simple']))
phoneset_ipa = []
phoneset_novo70 = []
with open(default.novo70_phoneset, "rt", encoding="utf-8") as fin:
lines = fin.read()
lines = lines.split('\n')
for line in lines:
words = line.split('\t')
if len(words) > 1:
novo70 = words[0]
ipa = words[1]
phoneset_ipa.append(ipa)
phoneset_novo70.append(novo70)
translation_key_ipa2novo70[ipa] = novo70
translation_key_novo702ipa[novo70] = ipa
phoneset_ipa = np.unique(phoneset_ipa)
phoneset_novo70 = np.unique(phoneset_novo70)
return phoneset_ipa, phoneset_novo70, translation_key_ipa2novo70, translation_key_novo702ipa
def multi_character_tokenize(line, multi_character_tokens):
"""
Tries to match one of the tokens in multi_character_tokens at each position of line,
starting at position 0,
if so tokenizes and eats that token. Otherwise tokenizes a single character.
Copied from forced_alignment.convert_phone_set.py
"""
while line != '':
for token in multi_character_tokens:
if line.startswith(token) and len(token) > 0:
yield token
line = line[len(token):]
break
else:
yield line[:1]
line = line[1:]
def split_ipa(line):
"""
Split a line by IPA phones.
If nasalized sound (such as ɛ̃ː) is included, it will give error.
:param string line: one line written in IPA.
:return string lineSeperated: the line splitted in IPA phone.
"""
multi_character_phones = [
# IPAs in CGN.
u'ʌu', u'ɛi', u'œy', u'aː', u'eː', u'iː', u'oː', u'øː', u'ɛː', u'œː', u'ɔː', u'ɛ̃ː', u'ɑ̃ː', u'ɔ̃ː', u'œ̃', u'ɪː'
]
return [phone for phone in multi_character_tokenize(line.strip(), multi_character_phones)]
def split_novo70(line):
"""
Split a line by novo70 phones.
:param string line: one line written in novo70.
:return string lineSeperated: the line splitted by novo70 phones.
"""
_, phoneset_novo70, _, _ = load_phonset()
multi_character_phones = [p for p in phoneset_novo70 if len(p) > 1]
multi_character_phones = sorted(multi_character_phones, key=len, reverse=True)
return ['sp' if phone == ' ' else phone
for phone in multi_character_tokenize(line.strip(), multi_character_phones)]
def novo702ipa(tokens):
pronunciation = []
_, _, _, translation_key = load_phonset()
for phone in split_novo70(tokens):
pronunciation.append(translation_key.get(phone, phone))
return ' '.join(pronunciation)
# numbering of novo70 should be checked.
def ipa2novo70(tokens):
pronunciation = []
_, _, translation_key, _ = load_phonset()
for phone in split_ipa(tokens):
pronunciation.append(translation_key.get(phone, phone))
return ' '.join(pronunciation)
def make_grammar(word, pronunciation_ipa):
"""
Args:
words
pronunciation_ipa: list of pronunciation variants.
"""
#word = 'pauw'
#pronunciation_ipa = ['pau', 'pɑu']
grammer_data_elements0_pronunciation = []
for id, ipa in enumerate(pronunciation_ipa):
novo70 = novoapi_functions.ipa2novo70(ipa)
grammer_data_elements0_pronunciation.append({
"phones": novo70.split(),
"id": id
})
grammar_data = {
"kind": 'sequence',
"elements": [{
"kind": "word",
"pronunciation": grammer_data_elements0_pronunciation,
"label": word
}]
}
grammar = {
"type": "confusion_network",
"version": "1.0",
"data": grammar_data,
"return_objects": ["grammar"],
"phoneset": "novo70"
}
return grammar