started to check which words in stimmen transcription consists of only phones in novo70 phoneset.

acoustic_model/check_novoapi.py

@@ -16,7 +16,7 @@ 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 
 
@@ -35,7 +35,7 @@ translation_key = dict()
 
 phoneset_ipa = []
 phoneset_novo70 = []
-with open(default.cmu69_phoneset, "rt", encoding="utf-8") as fin:
+with open(default.novo70_phoneset, "rt", encoding="utf-8") as fin:
 	lines = fin.read()
 	lines = lines.split('\n')
 	for line in lines:
@@ -49,6 +49,14 @@ with open(default.cmu69_phoneset, "rt", encoding="utf-8") as fin:
 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
+david_suggestion = ['ɔː', 'ɪː', 'iː', 'œː', 'ɛː']
+
 
 ## ======================= convert phones ======================
 mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', default.ipa_xsampa_converter_dir)
@@ -56,7 +64,38 @@ mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', default.ipa_xsampa_
 stimmen_transcription_ = pd.ExcelFile(default.stimmen_transcription_xlsx)
 df = pd.read_excel(stimmen_transcription_, 'check')
 #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))
+#        print('{0}: {1} - {2}'.format(xsampa, ipa_converted, ipa))
+transcription_ipa = list(df['IPA'])
+
+# transcription mistake?
+transcription_ipa = [ipa.replace(';', ':') 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 = []
+for ipa in transcription_ipa:
+	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_]
+
+	#translation_key.get(phone, phone)
+	not_in_novo70.extend(not_in_novo70_)
+not_in_novo70_list = list(set(not_in_novo70))
+
+
+def search_phone_ipa(x, phone_list):
+	return [phone for phone in phone_list if x in convert_phone_set.split_ipa(phone)]
+
+
+# 'ɐ', 'ɒ', 'w', 'æ', 'ʀ', 'ʁ', 
+# 'œː', 'ɾ', 
+# 'o', 'a'
+# [e] 'nyːver mɑntsjə' (1)
+# [ɹ] 'iːjəɹ' (2)
+
+search_phone_ipa('ˑ', transcription_ipa)

acoustic_model/defaultfiles.py

@@ -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')