Browse Source

confusion matrix is output.

master
yemaozi88 3 years ago
parent
commit
8efb091715
  1. BIN
      .vs/acoustic_model/v15/.suo
  2. BIN
      acoustic_model/__pycache__/defaultfiles.cpython-36.pyc
  3. 46
      acoustic_model/check_novoapi.py
  4. 1
      acoustic_model/defaultfiles.py

BIN
.vs/acoustic_model/v15/.suo

BIN
acoustic_model/__pycache__/defaultfiles.cpython-36.pyc

46
acoustic_model/check_novoapi.py

@ -3,23 +3,27 @@ os.chdir(r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model')
import sys
import csv
#import subprocess
#from collections import Counter
#import re
import numpy as np
import pandas as pd
#import matplotlib.pyplot as plt
#from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
import novoapi
from forced_alignment import pyhtk, convert_phone_set
import acoustic_model_functions as am_func
import convert_xsampa2ipa
import defaultfiles as default
import novoapi_functions
sys.path.append(default.accent_classification_dir)
import output_confusion_matrix
from forced_alignment import pyhtk, convert_phone_set
## procedure
forced_alignment_novo70 = True
import novoapi
import novoapi_functions
## ===== load novo phoneset =====
phoneset_ipa, phoneset_novo70, translation_key_ipa2novo70, translation_key_novo702ipa = novoapi_functions.load_phonset()
@ -145,9 +149,9 @@ for word in word_list:
## ===== forced alignment =====
if forced_alignment:
if forced_alignment_novo70:
Results = pd.DataFrame(index=[],
columns=['filename', 'ipa', 'word', 'result_ipa', 'result_novo70', 'llh'])
columns=['filename', 'word', 'ipa', 'result_ipa', 'result_novo70', 'llh'])
for word in word_list:
#for word in ['Oor']:
# pronunciation variants top 3
@ -176,7 +180,7 @@ if forced_alignment:
samples = df_.query("ipa in @pronunciation_ipa")
results = pd.DataFrame(index=[],
columns=['filename', 'ipa', 'word', 'result_ipa', 'result_novo70', 'llh'])
columns=['filename', 'word', 'ipa', 'result_ipa', 'result_novo70', 'llh'])
#j = 0
for i in range(0, len(samples)):
@ -205,5 +209,23 @@ if forced_alignment:
Results.to_excel(os.path.join(default.stimmen_dir, 'Results.xlsx'), encoding="utf-8")
else:
Results_xlsx = pd.ExcelFile(os.path.join(default.stimmen_dir, 'Results.xlsx'), encoding="utf-8")
R = pd.read_excel(Results_xlsx, 'Sheet1')
Results = pd.read_excel(Results_xlsx, 'Sheet1')
## ===== analysis =====
result_novoapi_dir = os.path.join(default.stimmen_dir, 'result', 'novoapi')
for word in word_list:
if not word == 'Oog':
#word = 'Reus'
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(result_novoapi_dir, word + '.png'))

1
acoustic_model/defaultfiles.py

@ -29,6 +29,7 @@ config_hvite = os.path.join(cygwin_dir, 'config', 'config.HVite')
repo_dir = r'C:\Users\Aki\source\repos'
ipa_xsampa_converter_dir = os.path.join(repo_dir, 'ipa-xsama-converter')
forced_alignment_module_dir = os.path.join(repo_dir, 'forced_alignment')
accent_classification_dir = os.path.join(repo_dir, 'accent_classification', 'accent_classification')
WSL_dir = r'C:\OneDrive\WSL'
fame_dir = os.path.join(WSL_dir, 'kaldi-trunk', 'egs', 'fame')

Loading…
Cancel
Save