FA result evaluation and xsampa to ipa conversion is updated.

acoustic_model/acoustic_model.py

@@ -22,11 +22,11 @@ dataset_list = ['devel', 'test', 'train']
 extract_features  = 0
 make_feature_list = 0
 conv_lexicon	  = 0
-check_lexicon	  = 0
+check_lexicon	  = 1
 make_mlf		  = 0
 combine_files	  = 0
 flat_start		  = 0
-train_model		  = 1
+train_model		  = 0
 forced_alignment  = 0
 
 
@@ -133,7 +133,11 @@ if check_lexicon:
 	print("==== check if all the phones are successfully converted. ====\n")
 
 	# the phones used in the lexicon.
-	phonelist = am_func.get_phonelist(lex_htk)
+	phonelist_asr = am_func.get_phonelist(lex_asr)
+	phonelist_oov = am_func.get_phonelist(lex_oov)
+	phonelist_htk = am_func.get_phonelist(lex_htk)
+
+	phonelist = phonelist_asr.union(phonelist_oov)
 
 	# the lines which include a specific phone.
 	lines = am_func.find_phone(lex_asr, 'g')

acoustic_model/performance_check.py

@@ -3,19 +3,54 @@ import sys
 import csv
 import subprocess
 import configparser
+from collections import Counter
 
 import numpy as np
 import pandas as pd
+import matplotlib.pyplot as plt
 
 
-## ======================= user define =======================
+## ======================= functions =======================
+
+def read_fileFA(fileFA):
+	"""
+	read the result file of HTK forced alignment.
+	this function only works when input is one word.
+	"""
+	with open(fileFA, 'r') as f:
+		lines = f.read()
+		lines = lines.split('\n')
+
+	phones = []
+	for line in lines:
+		line_split = line.split()
+		if len(line_split) > 1:
+			phones.append(line_split[2])
+
+	return ' '.join(phones)
+
+
+#####################
+##   USER DEFINE   ##
+#####################
 curr_dir   = r'C:\Users\Aki\source\repos\acoustic_model\acoustic_model'
 config_ini = curr_dir + '\\config.ini'
-forced_alignment_module  = r'C:\Users\Aki\source\repos\forced_alignment'
+forced_alignment_module     = r'C:\Users\Aki\source\repos\forced_alignment'
+forced_alignment_module_old = r'C:\OneDrive\Research\rug\code\forced_alignment\forced_alignment'
 ipa_xsampa_converter_dir = r'C:\Users\Aki\source\repos\ipa-xsama-converter'
+
 csvfile = r"C:\OneDrive\Research\rug\stimmen\Frisian Variants Picture Task Stimmen.csv"
+experiments_dir = r'C:\OneDrive\Research\rug\experiments'
+data_dir = experiments_dir + '\\stimmen\\data'
+cygwin_dir = r'C:\cygwin64\home\Aki\acoustic_model'
 
 # procedure
+convert_phones = 0
+make_dic_files = 0
+make_dic_files_short = 0
+do_forced_alignment = 0
+eval_forced_alignment = 1
+
 
 
 ## ======================= add paths =======================
@@ -28,6 +63,10 @@ sys.path.append(curr_dir)
 import convert_xsampa2ipa
 import acoustic_model_functions as am_func
 
+# for forced-alignment
+sys.path.append(forced_alignment_module_old)
+import pyHTK
+
 
 ## ======================= load variables =======================
 config = configparser.ConfigParser()
@@ -40,85 +79,179 @@ lex_asr		= FAME_dir + '\\lexicon\\lex.asr'
 lex_asr_htk = FAME_dir + '\\lexicon\\lex.asr_htk'
 
 
-## ======================= check phones included in FAME! =======================
-# the phones used in the lexicon.
-#phonelist = am_func.get_phonelist(lex_htk)
-
-# the lines which include a specific phone.
-#lines = am_func.find_phone(lex_asr, 'x')
-
-
 ## ======================= convert phones ======================
-mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', ipa_xsampa_converter_dir)
+if convert_phones:
+	mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', ipa_xsampa_converter_dir)
 
-with open(csvfile, encoding="utf-8") as fin:
+	## check phones included in FAME!
-	lines = csv.reader(fin, delimiter=';', lineterminator="\n", skipinitialspace=True)
+	# the phones used in the lexicon.
-	next(lines, None) # skip the headers
+	#phonelist = am_func.get_phonelist(lex_htk)
 
-	filenames	   = []
+	# the lines which include a specific phone.
-	words		   = []
+	#lines = am_func.find_phone(lex_asr, 'x')
-	pronunciations = []
+
-	for line in lines:
+	with open(csvfile, encoding="utf-8") as fin:
-		if line[1] is not '' and len(line) > 5:
+		lines = csv.reader(fin, delimiter=';', lineterminator="\n", skipinitialspace=True)
-			filenames.append(line[0])
+		next(lines, None) # skip the headers
-			words.append(line[1])
+
-			pron_xsampa = line[3]
+		filenames	   = []
-			pron_ipa = convert_xsampa2ipa.conversion('xsampa', 'ipa', mapping, pron_xsampa)
+		words		   = []
-			pron_ipa = pron_ipa.replace('ː', ':')
+		pronunciations = []
-			pron_famehtk = convert_phone_set.ipa2famehtk(pron_ipa)
+		for line in lines:
+			if line[1] is not '' and len(line) > 5:
+				filenames.append(line[0])
+				words.append(line[1])
+				pron_xsampa = line[3]
+				pron_ipa = convert_xsampa2ipa.conversion('xsampa', 'ipa', mapping, pron_xsampa)
+				pron_ipa = pron_ipa.replace('ː', ':')
+				pron_famehtk = convert_phone_set.ipa2famehtk(pron_ipa)
 			
-			# adjust to phones used in the acoustic model.
+				# adjust to phones used in the acoustic model.
-			pron_famehtk = pron_famehtk.replace('sp', 'sil')
+				pron_famehtk = pron_famehtk.replace('sp', 'sil')
-			pron_famehtk = pron_famehtk.replace('ce :', 'ce') # because ceh is ignored.
+				pron_famehtk = pron_famehtk.replace('ce :', 'ce') # because ceh is ignored.
-			pron_famehtk = pron_famehtk.replace('w :', 'wh')
+				pron_famehtk = pron_famehtk.replace('w :', 'wh')
-			pron_famehtk = pron_famehtk.replace('e :', 'eh')
+				pron_famehtk = pron_famehtk.replace('e :', 'eh')
-			pron_famehtk = pron_famehtk.replace('eh :', 'eh')
+				pron_famehtk = pron_famehtk.replace('eh :', 'eh')
-			pron_famehtk = pron_famehtk.replace('ih :', 'ih')
+				pron_famehtk = pron_famehtk.replace('ih :', 'ih')
 
-			#translation_key = {'sp': 'sil', 'ce :': 'ceh', 'w :': 'wh'}
+				#translation_key = {'sp': 'sil', 'ce :': 'ceh', 'w :': 'wh'}
-			#pron = []
+				#pron = []
-			#for phoneme in pron_famehtk.split(' '):
+				#for phoneme in pron_famehtk.split(' '):
-			#	pron.append(translation_key.get(phoneme, phoneme))
+				#	pron.append(translation_key.get(phoneme, phoneme))
-			#pronunciations.append(' '.join(pron_famehtk))
+				#pronunciations.append(' '.join(pron_famehtk))
-			pronunciations.append(pron_famehtk)
+				pronunciations.append(pron_famehtk)
 
-filenames	   = np.array(filenames)
+	# check if all phones are in the phonelist of the acoustic model.
-words		   = np.array(words)
+	#phonelist = ' '.join(pronunciations)
-pronunciations = np.array(pronunciations)
+	#np.unique(phonelist.split(' '))
+	#phonelist.find(':')
 
-del line, lines
+	filenames	   = np.array(filenames)
-del pron_xsampa, pron_ipa, pron_famehtk
+	words		   = np.array(words)
+	pronunciations = np.array(pronunciations)
 
-# check if all phones are in the phonelist of the acoustic model.
+	del line, lines
-#phonelist = ' '.join(pronunciations)
+	del pron_xsampa, pron_ipa, pron_famehtk
-#np.unique(phonelist.split(' '))
-#phonelist.find(':')
 
-# make dict files.
+	np.save(data_dir + '\\filenames.npy', filenames)
+	np.save(data_dir + '\\words.npy', words)
+	np.save(data_dir + '\\pronunciations.npy', pronunciations)
+else:
+	filenames	   = np.load(data_dir + '\\filenames.npy')
+	words		   = np.load(data_dir + '\\words.npy')
+	
+	pronunciations = np.load(data_dir + '\\pronunciations.npy')
 word_list = np.unique(words)
-word_id = 1
+
-word = word_list[word_id]
+
+## ======================= make dict files used for HTK. ======================
+if make_dic_files:
+	output_dir = experiments_dir + r'\stimmen\dic'
+
+	for word in word_list:
+		WORD	= word.upper()
+		fileDic = output_dir + '\\' + word + '.dic'
+
+		# make dic file.
+		pronvar_ = pronunciations[words == word]
+		pronvar  = np.unique(pronvar_)
+
+		with open(fileDic, 'w') as f:
+			for pvar in pronvar:
+				f.write('{0}\t{1}\n'.format(WORD, pvar))
+
+
+## ======================= make dict files for most popular words. ======================	
+if make_dic_files_short:
+	output_dir = experiments_dir + r'\stimmen\dic'
+
+	#word = word_list[3]
+	for word in word_list:
+		WORD	= word.upper()
+		fileStat = output_dir + '\\' + word + '_stat.csv'
+		
+		pronvar = pronunciations[words == word]
+		c = Counter(pronvar)
+		total_num = sum(c.values())
+
+		with open(fileStat, 'w') as f:
+			for key, value in c.items():
+				f.write('{0}\t{1:.2f}\t{2}\t{3}\n'.format(value, value/total_num*100, WORD, key))
 
 
 ## ======================= forced alignment =======================
-#if forced_alignment:
+if do_forced_alignment:
-#	try:
+	configHVite   = cygwin_dir + r'\config\config.HVite'
-#		scripts.run_command([
+	filePhoneList = experiments_dir + r'\friesian\acoustic_model\config\phonelist_friesian.txt'
-#			'HVite','-T', '1', '-a', '-C', configHVite,
+	wav_dir	= experiments_dir + r'\stimmen\wav'
-#			'-H', AcousticModel, '-m', '-I',
+
-#			mlf_file, '-i', fa_file, '-S',
+	#for hmm_num in [1, 2, 4, 8, 16, 32, 64, 128]:
-#			script_file, htk_dict_file, filePhoneList
+	for hmm_num in [64]:
-#		])
+		hmm_num_str = str(hmm_num)
-#	except:
+		AcousticModel = experiments_dir + r'\friesian\acoustic_model\model\hmm' + hmm_num_str + r'-3\hmmdefs'
-#		print("\033[91mHVite command failed with these input files:\033[0m")
+
-#		print(_debug_show_file('HVite config', configHVite))
+		predictions = []
-#		print(_debug_show_file('Accoustic model', AcousticModel))
+		file_num_max = len(filenames)
-#		print(_debug_show_file('Master Label file', mlf_file))
+		for i in range(0, file_num_max):
-#		print(_debug_show_file('Output', fa_file))
+			print('=== {0}/{1} ==='.format(i, file_num_max))
-#		print(_debug_show_file('Script file', script_file))
+			filename = filenames[i]
-#		print(_debug_show_file('HTK dictionary', htk_dict_file))
+			fileWav = wav_dir + '\\' + filename
-#		print(_debug_show_file('Phoneme list', filePhoneList))
+	
-#		raise
+			if os.path.exists(fileWav):
+				word = words[i]
+				WORD = word.upper()
+
+				# make label file.
+				fileLab = wav_dir + '\\' + filename.replace('.wav', '.lab') 
+				with open(fileLab, 'w') as f:
+					lines = f.write(WORD)
+
+				fileDic = experiments_dir + r'\stimmen\dic_short' + '\\' + word + '.dic'
+				fileFA  = experiments_dir + r'\stimmen\FA_short' + '\\' + filename.replace('.wav', '.txt') + hmm_num_str
+
+				pyHTK.doHVite(fileWav, fileLab, fileDic, fileFA, configHVite, filePhoneList, AcousticModel)
+				prediction = read_fileFA(fileFA)
+				predictions.append(prediction)
+
+				os.remove(fileLab)
+				print('{0}: {1} -> {2}'.format(WORD, pronunciations[i], prediction))
+			else:
+				predictions.append('')
+				print('!!!!! file not found.')
+
+		predictions = np.array(predictions)
+		match = np.c_[words[predictions != ''], pronunciations[predictions != ''], predictions[predictions != '']]
+		np.save(data_dir + '\\match_hmm' + hmm_num_str + '.npy', match)
 
 
-##os.remove(hcopy_scp.name)
+## ======================= evaluate the result of forced alignment =======================
+if eval_forced_alignment:
+
+	#for hmm_num in [1, 2, 4, 8, 16, 32, 64]:
+	hmm_num = 64
+	hmm_num_str = str(hmm_num)
+	match = np.load(data_dir + '\\match_hmm' + hmm_num_str + '.npy')
+	
+	# use dic_short?
+	if 1:
+		pronunciation_variants = np.array(['WORD', 'pronunciation']).reshape(1, 2)
+		for word in word_list:
+			fileDic = experiments_dir + r'\stimmen\dic_short' + '\\' + word + '.dic'
+			pronunciation_variants = np.r_[pronunciation_variants, pyHTK.loadHTKdic(fileDic)]
+
+		match_short = []
+		for line in match:
+			word = line[0]
+			WORD = word.upper()
+			pronvar = pronunciation_variants[pronunciation_variants[:, 0] == word.upper(), 1]
+		
+			if line[1] in pronvar:
+				match_short.append(line)
+
+		match_short = np.array(match_short)
+		match = np.copy(match_short)
+
+	# number of match
+	total_match = sum(match[:, 1] == match[:, 2])
+	print("{}: {}/{}".format(hmm_num_str, total_match, match.shape[0]))
+