250 lines
8.4 KiB
Python
250 lines
8.4 KiB
Python
import os
|
||
os.chdir(r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model')
|
||
|
||
import sys
|
||
import csv
|
||
from collections import Counter
|
||
import random
|
||
import shutil
|
||
|
||
import numpy as np
|
||
import pandas as pd
|
||
import matplotlib.pyplot as plt
|
||
from sklearn.metrics import confusion_matrix
|
||
from sklearn.metrics import accuracy_score
|
||
import novoapi
|
||
|
||
import defaultfiles as default
|
||
sys.path.append(default.forced_alignment_module_dir)
|
||
from forced_alignment import convert_phone_set
|
||
#import acoustic_model_functions as am_func
|
||
import convert_xsampa2ipa
|
||
import novoapi_functions
|
||
sys.path.append(default.accent_classification_dir)
|
||
import output_confusion_matrix
|
||
|
||
## procedure
|
||
forced_alignment_novo70 = True
|
||
balance_sample_numbers = False
|
||
|
||
|
||
## ===== load novo phoneset =====
|
||
phoneset_ipa, phoneset_novo70, translation_key_ipa2novo70, translation_key_novo702ipa = novoapi_functions.load_phonset()
|
||
|
||
|
||
## ===== 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.
|
||
stimmen_transcription_ = pd.ExcelFile(default.stimmen_transcription_xlsx)
|
||
df = pd.read_excel(stimmen_transcription_, 'frequency')
|
||
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)
|
||
|
||
# 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
|
||
# '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)
|
||
|
||
|
||
## ===== load all transcriptions (df) =====
|
||
df = pd.read_excel(stimmen_transcription_, 'original')
|
||
|
||
# mapping from ipa to xsampa
|
||
mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', default.ipa_xsampa_converter_dir)
|
||
#for xsampa, ipa in zip(df['X-SAMPA'], df['IPA']):
|
||
# ipa_converted = convert_xsampa2ipa.xsampa2ipa(mapping, xsampa)
|
||
# if not ipa_converted == ipa:
|
||
# print('{0}: {1} - {2}'.format(xsampa, ipa_converted, ipa))
|
||
|
||
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)})
|
||
|
||
word_list = [i for i in list(set(df['word'])) if not pd.isnull(i)]
|
||
word_list = sorted(word_list)
|
||
|
||
|
||
## check frequency of each pronunciation variants
|
||
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)
|
||
|
||
# each word
|
||
df_per_word = pd.DataFrame(index=[], columns=df_samples.keys())
|
||
|
||
for word in word_list:
|
||
df_samples_ = df_samples[df_samples['word']==word]
|
||
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")
|
||
|
||
|
||
## ===== forced alignment =====
|
||
rozen_dir = r'c:\Users\Aki\source\repos\acoustic_model\rozen-test'
|
||
if forced_alignment_novo70:
|
||
Results = pd.DataFrame(index=[],
|
||
columns=['filename', 'word', 'xsampa', 'ipa', 'result_ipa', 'result_novo70', 'llh'])
|
||
#for word in word_list:
|
||
for word in ['Rozen']:
|
||
# pronunciation variants top 3
|
||
df_per_word_ = df_per_word[df_per_word['word']==word]
|
||
df_per_word_ = df_per_word_.sort_values('frequency', ascending=False)
|
||
if len(df_per_word_) < 3: # pauw, rozen
|
||
pronunciation_ipa = list(df_per_word_['ipa'])
|
||
elif word=='Reuzenrad':
|
||
pronunciation_ipa = [
|
||
df_per_word_.iloc[0]['ipa'],
|
||
df_per_word_.iloc[1]['ipa'],
|
||
df_per_word_.iloc[2]['ipa'],
|
||
df_per_word_.iloc[3]['ipa']]
|
||
else:
|
||
# oog, oor, reus, roeiboot
|
||
pronunciation_ipa = [
|
||
df_per_word_.iloc[0]['ipa'],
|
||
df_per_word_.iloc[1]['ipa'],
|
||
df_per_word_.iloc[2]['ipa']]
|
||
#print("{0}: {1}".format(word, pronunciation_ipa))
|
||
|
||
# samples for the word
|
||
df_ = df[df['word']==word]
|
||
|
||
# samples in which all pronunciations are written in novo70.
|
||
samples = df_.query("ipa in @pronunciation_ipa")
|
||
|
||
|
||
## ===== balance sample numbers =====
|
||
if balance_sample_numbers:
|
||
c = Counter(samples['ipa'])
|
||
sample_num_list = [c[key] for key in c.keys()]
|
||
sample_num = np.min(sample_num_list)
|
||
|
||
samples_balanced = pd.DataFrame(index=[], columns=list(samples.keys()))
|
||
for key in c.keys():
|
||
samples_ = samples[samples['ipa'] == key]
|
||
samples_balanced = samples_balanced.append(samples_.sample(sample_num), ignore_index = True)
|
||
|
||
samples = samples_balanced
|
||
|
||
|
||
results = pd.DataFrame(index=[],
|
||
columns=['filename', 'word', 'xsampa', 'ipa', 'result_ipa', 'result_novo70', 'llh'])
|
||
|
||
for i in range(0, len(samples)):
|
||
sample = samples.iloc[i]
|
||
filename = sample['filename']
|
||
wav_file = os.path.join(default.stimmen_wav_dir, filename)
|
||
if os.path.exists(wav_file):
|
||
# for Martijn
|
||
shutil.copy(wav_file, os.path.join(rozen_dir, filename))
|
||
|
||
# pronunciation_ipa_ = [ipa.replace(':', 'ː') for ipa in pronunciation_ipa]
|
||
# result = novoapi_functions.forced_alignment(wav_file, word, pronunciation_ipa_)
|
||
# result_ipa, result_novo70, llh = novoapi_functions.result2pronunciation(result, word)
|
||
# result_ = pd.Series([
|
||
# sample['filename'],
|
||
# sample['word'],
|
||
# sample['xsampa'],
|
||
# sample['ipa'],
|
||
# ' '.join(result_ipa),
|
||
# ' '.join(result_novo70),
|
||
# llh
|
||
# ], index=results.columns)
|
||
# results = results.append(result_, ignore_index = True)
|
||
# print('{0}/{1}: answer {2} - prediction {3}'.format(
|
||
# i+1, len(samples), result_['ipa'], result_['result_ipa']))
|
||
# #results.to_excel(os.path.join(default.stimmen_dir, 'results.xlsx'), encoding="utf-8")
|
||
#if len(results) > 0:
|
||
# Results = Results.append(results, ignore_index = True)
|
||
#Results.to_excel(os.path.join(default.stimmen_result_novoapi_dir, 'Results.xlsx'), encoding="utf-8")
|
||
else:
|
||
Results_xlsx = pd.ExcelFile(os.path.join(default.stimmen_result_novoapi_dir, 'Results.xlsx'), encoding="utf-8")
|
||
Results = pd.read_excel(Results_xlsx, 'Sheet1')
|
||
|
||
|
||
## ===== analysis =====
|
||
#for word in word_list:
|
||
# if not word == 'Oog':
|
||
# Results_ = Results[Results['word'] == word]
|
||
# y_true = list(Results_['ipa'])
|
||
# y_pred_ = [ipa.replace(' ', '') for ipa in list(Results_['result_ipa'])]
|
||
# y_pred = [ipa.replace('ː', ':') for ipa in y_pred_]
|
||
# pronunciation_variants = list(set(y_true))
|
||
# cm = confusion_matrix(y_true, y_pred, labels=pronunciation_variants)
|
||
|
||
# plt.figure()
|
||
# output_confusion_matrix.plot_confusion_matrix(cm, pronunciation_variants, normalize=False)
|
||
# #plt.show()
|
||
# plt.savefig(os.path.join(default.stimmen_result_novoapi_dir, word + '.png')) |