forced alignment by novoapi is performed.

acoustic_model/check_novoapi.py

@@ -139,6 +139,71 @@ 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']>1]
+	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")
+
+
+## ===== forced alignment =====
+if forced_alignment:
+	Results = pd.DataFrame(index=[],
+		columns=['filename', 'ipa', 'word', 'result_ipa', 'result_novo70', 'llh'])
+	for word in word_list:
+	#for word in ['Oor']:
+		# 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")
+
+		results = pd.DataFrame(index=[],
+			columns=['filename', 'ipa', 'word', 'result_ipa', 'result_novo70', 'llh'])
+	
+		#j = 0
+		for i in range(0, len(samples)):
+			sample = samples.iloc[i]
+			wav_file = os.path.join(default.stimmen_wav_dir, sample['filename'])
+			if os.path.exists(wav_file):
+				#j += 1
+				#print('{0} - {1}'.format(word, i))
+				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['ipa'],
+					sample['word'],
+					' '.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']))
+
+		if len(results) > 0:
+			Results = Results.append(results, ignore_index = True)
+		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')
+

acoustic_model/novoapi_functions.py

@@ -36,10 +36,29 @@ def load_phonset():
 				phoneset_novo70.append(novo70)
 				translation_key_ipa2novo70[ipa] = novo70
 				translation_key_novo702ipa[novo70] = ipa
+
+	# As per Nederlandse phoneset_aki.xlsx recieved from David
+	# [ɔː] oh / ohr # from ipa->novo70, only oh is used.
+	# [ɪː] ih / ihr # from ipa->novo70, only ih is used.
+	# [iː] iy
+	# [œː] uh
+	# [ɛː] eh
+	# [w] wv in IPA written as ʋ. 
+	extra_ipa	 = ['ɔː', 'ɪː', 'iː', 'œː', 'ɛː', 'ʋ']
+	extra_novo70 = ['oh', 'ih', 'iy', 'uh', 'eh', 'wv'] 
+	for ipa, novo70 in zip(extra_ipa, extra_novo70):
+		phoneset_ipa.append(ipa)
+		phoneset_novo70.append(novo70)
+		translation_key_ipa2novo70[ipa] = novo70
+		translation_key_novo702ipa[novo70] = ipa
+
+	translation_key_novo702ipa['ohr'] = 'ɔː'
+	translation_key_novo702ipa['ihr'] = 'ɪː'
+
 	phoneset_ipa    = np.unique(phoneset_ipa)
 	phoneset_novo70 = np.unique(phoneset_novo70)
 
-	return 
+	return phoneset_ipa, phoneset_novo70, translation_key_ipa2novo70, translation_key_novo702ipa
 
 
 def multi_character_tokenize(line, multi_character_tokens):