def test_merge(self):
dacn = DialogueActConfusionNetwork()
dacn.add(0.05, DialogueActItem(dai='inform(food=chinese)'))
dacn.add(0.9, DialogueActItem(dai='inform(food=czech)'))
dacn.add(0.00005, DialogueActItem(dai='inform(food=russian)'))
dacn.merge(dacn, combine='max')
# Russian food should be pruned.
dacn.sort().prune()
self.assertTrue(not DialogueActItem(dai='inform(food=russian)') in dacn)
def test_sort(self):
dacn = DialogueActConfusionNetwork()
dacn.add(0.05, DialogueActItem(dai='inform(food=chinese)'))
dacn.add(1.0, DialogueActItem(dai='inform(food=czech)'))
dacn.add(0.00005, DialogueActItem(dai='inform(food=russian)'))
dacn.sort()
cn = list(dacn)
self.assertEqual(cn[0][1], DialogueActItem(dai='inform(food=czech)'))
self.assertEqual(cn[1][1], DialogueActItem(dai='inform(food=chinese)'))
self.assertEqual(cn[2][1], DialogueActItem(dai='inform(food=russian)'))
def test_merge(self):
dacn = DialogueActConfusionNetwork()
dacn.add(0.05, DialogueActItem(dai='inform(food=chinese)'))
dacn.add(0.9, DialogueActItem(dai='inform(food=czech)'))
dacn.add(0.00005, DialogueActItem(dai='inform(food=russian)'))
dacn.merge(dacn, combine='max')
# Russian food should be pruned.
dacn.sort().prune()
self.assertTrue(not DialogueActItem(
dai='inform(food=russian)') in dacn)
def test_sort(self):
dacn = DialogueActConfusionNetwork()
dacn.add(0.05, DialogueActItem(dai='inform(food=chinese)'))
dacn.add(1.0, DialogueActItem(dai='inform(food=czech)'))
dacn.add(0.00005, DialogueActItem(dai='inform(food=russian)'))
dacn.sort()
cn = list(dacn)
self.assertEqual(cn[0][1], DialogueActItem(dai='inform(food=czech)'))
self.assertEqual(cn[1][1], DialogueActItem(dai='inform(food=chinese)'))
self.assertEqual(cn[2][1], DialogueActItem(dai='inform(food=russian)'))
def parse_nblist(self, obs, *args, **kwargs):
"""
Parses an observation featuring an utterance n-best list using the
parse_1_best method.
Arguments:
obs -- a dictionary of observations
:: observation type -> observed value
where observation type is one of values for `obs_type' used in
`ft_props', and observed value is the corresponding observed
value for the input
args -- further positional arguments that should be passed to the
`parse_1_best' method call
kwargs -- further keyword arguments that should be passed to the
`parse_1_best' method call
"""
nblist = obs['utt_nbl']
if len(nblist) == 0:
return DialogueActConfusionNetwork()
obs_wo_nblist = copy.deepcopy(obs)
del obs_wo_nblist['utt_nbl']
dacn_list = []
for prob, utt in nblist:
if "_other_" == utt:
dacn = DialogueActConfusionNetwork()
dacn.add(1.0, DialogueActItem("other"))
elif "_silence_" == utt:
dacn = DialogueActConfusionNetwork()
dacn.add(1.0, DialogueActItem("silence"))
else:
obs_wo_nblist['utt'] = utt
dacn = self.parse_1_best(obs_wo_nblist, *args, **kwargs)
dacn_list.append((prob, dacn))
dacn = merge_slu_confnets(dacn_list)
dacn.prune()
dacn.sort()
return dacn
def parse_nblist(self, obs, *args, **kwargs):
"""
Parses an observation featuring an utterance n-best list using the
parse_1_best method.
Arguments:
obs -- a dictionary of observations
:: observation type -> observed value
where observation type is one of values for `obs_type' used in
`ft_props', and observed value is the corresponding observed
value for the input
args -- further positional arguments that should be passed to the
`parse_1_best' method call
kwargs -- further keyword arguments that should be passed to the
`parse_1_best' method call
"""
nblist = obs['utt_nbl']
if len(nblist) == 0:
return DialogueActConfusionNetwork()
obs_wo_nblist = copy.deepcopy(obs)
del obs_wo_nblist['utt_nbl']
dacn_list = []
for prob, utt in nblist:
if "_other_" == utt:
dacn = DialogueActConfusionNetwork()
dacn.add(1.0, DialogueActItem("other"))
elif "_silence_" == utt:
dacn = DialogueActConfusionNetwork()
dacn.add(1.0, DialogueActItem("silence"))
else:
obs_wo_nblist['utt'] = utt
dacn = self.parse_1_best(obs_wo_nblist, *args, **kwargs)
dacn_list.append((prob, dacn))
dacn = merge_slu_confnets(dacn_list)
dacn.prune()
dacn.sort()
return dacn
def parse_X(self, utterance, verbose=False):
if verbose:
print '='*120
print 'Parsing X'
print '-'*120
print unicode(utterance)
if self.preprocessing:
utterance = self.preprocessing.normalise(utterance)
utterance_fvcs = self.get_fvc(utterance)
if verbose:
print unicode(utterance)
print unicode(utterance_fvcs)
da_confnet = DialogueActConfusionNetwork()
for clser in self.trained_classifiers:
if verbose:
print "Using classifier: ", unicode(clser)
if self.parsed_classifiers[clser].value and self.parsed_classifiers[clser].value.startswith('CL_'):
# process abstracted classifiers
for f, v, c in utterance_fvcs:
cc = "CL_" + c.upper()
if self.parsed_classifiers[clser].value == cc:
#print clser, f, v, c
classifiers_features = self.get_features(utterance, (f, v, cc), utterance_fvcs)
classifiers_inputs = np.zeros((1, len(self.classifiers_features_mapping[clser])))
classifiers_inputs[0] = classifiers_features.get_feature_vector(self.classifiers_features_mapping[clser])
#if verbose:
# print classifiers_features
# print self.classifiers_features_mapping[clser]
p = self.trained_classifiers[clser].predict_proba(classifiers_inputs)
if verbose:
print ' Probability:', p
dai = DialogueActItem(self.parsed_classifiers[clser].dat, self.parsed_classifiers[clser].name, v)
da_confnet.add_merge(p[0][1], dai, combine='max')
else:
# process concrete classifiers
classifiers_features = self.get_features(utterance, (None, None, None), utterance_fvcs)
classifiers_inputs = np.zeros((1, len(self.classifiers_features_mapping[clser])))
classifiers_inputs[0] = classifiers_features.get_feature_vector(self.classifiers_features_mapping[clser])
#if verbose:
# print classifiers_features
# print self.classifiers_features_mapping[clser]
p = self.trained_classifiers[clser].predict_proba(classifiers_inputs)
if verbose:
print ' Probability:', p
dai = self.parsed_classifiers[clser]
da_confnet.add_merge(p[0][1], dai, combine='max')
da_confnet.sort().prune()
return da_confnet
def parse_X(self, utterance, verbose=False):
if verbose:
print '=' * 120
print 'Parsing X'
print '-' * 120
print unicode(utterance)
if self.preprocessing:
utterance = self.preprocessing.normalise(utterance)
utterance_fvcs = self.get_fvc(utterance)
if verbose:
print unicode(utterance)
print unicode(utterance_fvcs)
da_confnet = DialogueActConfusionNetwork()
for clser in self.trained_classifiers:
if verbose:
print "Using classifier: ", unicode(clser)
if self.parsed_classifiers[clser].value and self.parsed_classifiers[
clser].value.startswith('CL_'):
# process abstracted classifiers
for f, v, c in utterance_fvcs:
cc = "CL_" + c.upper()
if self.parsed_classifiers[clser].value == cc:
#print clser, f, v, c
classifiers_features = self.get_features(
utterance, (f, v, cc), utterance_fvcs)
classifiers_inputs = np.zeros(
(1, len(self.classifiers_features_mapping[clser])))
classifiers_inputs[
0] = classifiers_features.get_feature_vector(
self.classifiers_features_mapping[clser])
#if verbose:
# print classifiers_features
# print self.classifiers_features_mapping[clser]
p = self.trained_classifiers[clser].predict_proba(
classifiers_inputs)
if verbose:
print ' Probability:', p
dai = DialogueActItem(
self.parsed_classifiers[clser].dat,
self.parsed_classifiers[clser].name, v)
da_confnet.add_merge(p[0][1], dai, combine='max')
else:
# process concrete classifiers
classifiers_features = self.get_features(
utterance, (None, None, None), utterance_fvcs)
classifiers_inputs = np.zeros(
(1, len(self.classifiers_features_mapping[clser])))
classifiers_inputs[
0] = classifiers_features.get_feature_vector(
self.classifiers_features_mapping[clser])
#if verbose:
# print classifiers_features
# print self.classifiers_features_mapping[clser]
p = self.trained_classifiers[clser].predict_proba(
classifiers_inputs)
if verbose:
print ' Probability:', p
dai = self.parsed_classifiers[clser]
da_confnet.add_merge(p[0][1], dai, combine='max')
da_confnet.sort().prune()
return da_confnet
def test_session_logger(self):
cfg = Config.load_configs(config=CONFIG_DICT, use_default=False)
sl = SessionLogger()
# test 3 calls at once
for i in range(3):
sess_dir = "./%d" % i
if not os.path.isdir(sess_dir):
os.mkdir(sess_dir)
sl.session_start(sess_dir)
sl.config('config = ' + unicode(cfg))
sl.header(cfg['Logging']["system_name"], cfg['Logging']["version"])
sl.input_source("voip")
sl.dialogue_rec_start(None, "both_complete_dialogue.wav")
sl.dialogue_rec_start("system", "system_complete_dialogue.wav")
sl.dialogue_rec_start("user", "user_complete_dialogue.wav")
sl.dialogue_rec_end("both_complete_dialogue.wav")
sl.dialogue_rec_end("system_complete_dialogue.wav")
sl.dialogue_rec_end("user_complete_dialogue.wav")
sl.turn("system")
sl.dialogue_act("system", "hello()")
sl.text("system", "Hello.")
sl.rec_start("system", "system1.wav")
sl.rec_end("system1.wav")
sl.turn("user")
sl.rec_start("user", "user1.wav")
sl.rec_end("user1.wav")
A1, A2, A3 = 0.90, 0.05, 0.05
B1, B2, B3 = 0.70, 0.20, 0.10
C1, C2, C3 = 0.80, 0.10, 0.10
asr_confnet = UtteranceConfusionNetwork()
asr_confnet.add([[A1, "want"], [A2, "has"], [A3, 'ehm']])
asr_confnet.add([[B1, "Chinese"], [B2, "English"], [B3, 'cheap']])
asr_confnet.add([[C1, "restaurant"], [C2, "pub"], [C3, 'hotel']])
asr_confnet.merge()
asr_confnet.normalise()
asr_confnet.sort()
asr_nblist = asr_confnet.get_utterance_nblist()
sl.asr("user", "user1.wav", asr_nblist, asr_confnet)
slu_confnet = DialogueActConfusionNetwork()
slu_confnet.add(0.7, DialogueActItem('hello'))
slu_confnet.add(0.6, DialogueActItem('thankyou'))
slu_confnet.add(0.4, DialogueActItem('restart'))
slu_confnet.add(0.1, DialogueActItem('bye'))
slu_confnet.merge()
slu_confnet.normalise()
slu_confnet.sort()
slu_nblist = slu_confnet.get_da_nblist()
sl.slu("user", "user1.wav", slu_nblist, slu_confnet)
sl.turn("system")
sl.dialogue_act("system", "thankyou()")
sl.text("system", "Thank you.", cost = 1.0)
sl.rec_start("system", "system2.wav")
sl.rec_end("system2.wav")
sl.barge_in("system", tts_time = True)
sl.turn("user")
sl.rec_start("user", "user2.wav")
sl.rec_end("user2.wav")
sl.hangup("user")
def test_session_logger(self):
cfg = Config.load_configs(config=CONFIG_DICT, use_default=False)
sl = SessionLogger()
# test 3 calls at once
for i in range(3):
sess_dir = "./%d" % i
if not os.path.isdir(sess_dir):
os.mkdir(sess_dir)
sl.session_start(sess_dir)
sl.config('config = ' + unicode(cfg))
sl.header(cfg['Logging']["system_name"], cfg['Logging']["version"])
sl.input_source("voip")
sl.dialogue_rec_start(None, "both_complete_dialogue.wav")
sl.dialogue_rec_start("system", "system_complete_dialogue.wav")
sl.dialogue_rec_start("user", "user_complete_dialogue.wav")
sl.dialogue_rec_end("both_complete_dialogue.wav")
sl.dialogue_rec_end("system_complete_dialogue.wav")
sl.dialogue_rec_end("user_complete_dialogue.wav")
sl.turn("system")
sl.dialogue_act("system", "hello()")
sl.text("system", "Hello.")
sl.rec_start("system", "system1.wav")
sl.rec_end("system1.wav")
sl.turn("user")
sl.rec_start("user", "user1.wav")
sl.rec_end("user1.wav")
A1, A2, A3 = 0.90, 0.05, 0.05
B1, B2, B3 = 0.70, 0.20, 0.10
C1, C2, C3 = 0.80, 0.10, 0.10
asr_confnet = UtteranceConfusionNetwork()
asr_confnet.add([[A1, "want"], [A2, "has"], [A3, 'ehm']])
asr_confnet.add([[B1, "Chinese"], [B2, "English"], [B3, 'cheap']])
asr_confnet.add([[C1, "restaurant"], [C2, "pub"], [C3, 'hotel']])
asr_confnet.merge()
asr_confnet.normalise()
asr_confnet.sort()
asr_nblist = asr_confnet.get_utterance_nblist()
sl.asr("user", "user1.wav", asr_nblist, asr_confnet)
slu_confnet = DialogueActConfusionNetwork()
slu_confnet.add(0.7, DialogueActItem('hello'))
slu_confnet.add(0.6, DialogueActItem('thankyou'))
slu_confnet.add(0.4, DialogueActItem('restart'))
slu_confnet.add(0.1, DialogueActItem('bye'))
slu_confnet.merge()
slu_confnet.normalise()
slu_confnet.sort()
slu_nblist = slu_confnet.get_da_nblist()
sl.slu("user", "user1.wav", slu_nblist, slu_confnet)
sl.turn("system")
sl.dialogue_act("system", "thankyou()")
sl.text("system", "Thank you.", cost=1.0)
sl.rec_start("system", "system2.wav")
sl.rec_end("system2.wav")
sl.barge_in("system", tts_time=True)
sl.turn("user")
sl.rec_start("user", "user2.wav")
sl.rec_end("user2.wav")
sl.hangup("user")
