def main():
import autopath
cfg = Config.load_configs(['resources/default-lz.cfg'],
use_default=False,
project_root=True)
#cfg = {'DM': {'UfalRuleDM':
# {'ontology':"/xdisk/devel/vystadial/alex/applications/" + \
# "CamInfoRest/ontology.cfg",
# 'db_cfg': "/xdisk/devel/vystadial/alex/applications/" + \
# "CamInfoRest/cued_data/CIRdbase_V7_noloc.txt"}}}
u = UfalRuleDM(cfg)
# ufal_ds = u.create_ds()
while 1:
curr_acts = DialogueActNBList()
for ln in sys.stdin:
if len(ln.strip()) == 0:
break
ln = ln.strip()
print ln
score, act = ln.split(" ", 1)
score = float(score)
curr_acts.add(score, DialogueActItem(dai=act))
u.da_in(curr_acts)
print " >", u.da_out()
def test_tecto_template_nlg(self):
# initialize
cfg = Config.load_configs(config=CONFIG_DICT,
use_default=False,
log=False)
nlg = TectoTemplateNLG(cfg)
# test all cases
for da, correct_text in zip(DAS, TEXTS):
# try generation
da = DialogueAct(da)
generated_text = nlg.generate(da)
# print output
s = []
s.append("")
s.append("Input DA:")
s.append(unicode(da))
s.append("")
s.append("Correct text:")
s.append(correct_text)
s.append("")
s.append("Generated text:")
s.append(generated_text)
s.append("")
# test the result
self.assertEqual(correct_text, generated_text)
def test_tecto_template_nlg(self):
# initialize
cfg = Config.load_configs(config=CONFIG_DICT, use_default=False,
log=False)
nlg = TectoTemplateNLG(cfg)
# test all cases
for da, correct_text in zip(DAS, TEXTS):
# try generation
da = DialogueAct(da)
generated_text = nlg.generate(da)
# print output
s = []
s.append("")
s.append("Input DA:")
s.append(unicode(da))
s.append("")
s.append("Correct text:")
s.append(correct_text)
s.append("")
s.append("Generated text:")
s.append(generated_text)
s.append("")
# test the result
self.assertEqual(correct_text, generated_text)
def _get_cfg(self):
cfg = Config(config={
'PublicTransportInfoCS': {
'max_turns': 120,
},
'DM': {
'directions': {
'type': directions.GoogleDirectionsFinder,
},
'dialogue_policy': {
'PTICSHDCPolicy': {
'accept_prob': 0.5,
'accept_prob_being_requested': 0.5,
'accept_prob_being_confirmed': 0.5,
'accept_prob_ludait': 0.5,
'accept_prob_noninformed': 0.5,
'confirm_prob': 0.5,
'select_prob': 0.5,
'min_change_prob': 0.5
}
},
'dialogue_state': {
'type': DeterministicDiscriminativeDialogueState,
},
'DeterministicDiscriminativeDialogueState': {
'type': 'UFAL_DSTC_1.0_approx',
},
'ontology': as_project_path('applications/PublicTransportInfoCS/data/ontology.py'),
},
'Logging': {
'system_logger': alex.utils.DummyLogger(),
'session_logger': alex.utils.DummyLogger()
},
'weather': {
'dictionary': as_project_path('applications/PublicTransportInfoCS/weather_cs.cfg'),
'suffix': 'CZ',
'units': 'celsius',
}
})
return cfg
def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
AudioHub runs the spoken dialog system, using your microphone and speakers.
The default configuration is loaded from '<app root>/resources/default.cfg'.
Additional configuration parameters can be passed as an argument '-c'.
Any additional config parameters overwrite their previous values.
""")
parser.add_argument('-c', "--configs", nargs="+",
help='additional configuration file')
args = parser.parse_args()
cfg = Config.load_configs(args.configs)
cfg['Logging']['system_logger'].info("Voip Hub\n" + "=" * 120)
vhub = AudioHub(cfg)
vhub.run()
def main():
cfg = Config.load_configs(['resources/default-lz.cfg'],
use_default=False, project_root=True)
#cfg = {'DM': {'UfalRuleDM':
# {'ontology':"/xdisk/devel/vystadial/alex/applications/" + \
# "CamInfoRest/ontology.cfg",
# 'db_cfg': "/xdisk/devel/vystadial/alex/applications/" + \
# "CamInfoRest/cued_data/CIRdbase_V7_noloc.txt"}}}
u = UfalRuleDM(cfg)
# ufal_ds = u.create_ds()
while 1:
curr_acts = DialogueActNBList()
for ln in sys.stdin:
if len(ln.strip()) == 0:
break
ln = ln.strip()
print ln
score, act = ln.split(" ", 1)
score = float(score)
curr_acts.add(score, DialogueActItem(dai=act))
u.da_in(curr_acts)
print " >", u.da_out()
def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
AudioHub runs the spoken dialog system, using your microphone and speakers.
The default configuration is loaded from '<app root>/resources/default.cfg'.
Additional configuration parameters can be passed as an argument '-c'.
Any additional config parameters overwrite their previous values.
""")
parser.add_argument('-c',
"--configs",
nargs="+",
help='additional configuration file')
args = parser.parse_args()
cfg = Config.load_configs(args.configs)
cfg['Logging']['system_logger'].info("Voip Hub\n" + "=" * 120)
vhub = AudioHub(cfg)
vhub.run()
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 main():
from alex.utils.config import Config
from alex.utils.caminfodb import CamInfoDb
# This implicitly loads also the default config.
cfg = Config.load_configs(['resources/lz.cfg'], project_root=True)
db_cfg = cfg['DM']["PUfalRuleDM"]['db_cfg'] # database provider
db = CamInfoDb(db_cfg)
pdm = PRuleDM(cfg, db)
pdm.new_dialogue()
pdm.da_out()
# user's input
cn = DialogueActConfusionNetwork()
cn.add(0.7, DialogueActItem(dai="inform(food=chinese)"))
cn.add(0.2, DialogueActItem(dai="inform(food=indian)"))
cn.add(0.5, DialogueActItem(dai="inform(food=chinese)"))
cn.add(0.1, DialogueActItem(dai="inform(food=czech)"))
cn.add(0.1, DialogueActItem(dai="confirm(food=czech)"))
cn.add(0.6, DialogueActItem(dai="request(phone)"))
cn.add(0.3, DialogueActItem(dai="reset()"))
cn.add(0.3, DialogueActItem(dai="asdf()"))
cn.add(0.3, DialogueActItem(dai="reset()"))
print cn
pdm.da_in(cn)
pdm.da_out()
cn = DialogueActConfusionNetwork()
cn.add(0.99, DialogueActItem(dai="confirm(food=indian)"))
print cn
pdm.da_in(cn)
pdm.da_out()
cn = DialogueActConfusionNetwork()
cn.add(0.77, DialogueActItem(dai="reqalts()"))
print cn
pdm.da_in(cn)
pdm.da_out()
cn = DialogueActConfusionNetwork()
cn.add(0.77, DialogueActItem(dai="reqalts()"))
print cn
pdm.da_in(cn)
pdm.da_out()
cn = DialogueActConfusionNetwork()
cn.add(0.99, DialogueActItem(dai="confirm(food=indian)"))
print cn
pdm.da_in(cn)
pdm.da_out()
cn = DialogueActConfusionNetwork()
cn.add(0.99, DialogueActItem(dai="request(name)"))
cn.add(0.99, DialogueActItem(dai="request(food)"))
print cn
pdm.da_in(cn)
pdm.da_out()
cn = DialogueActConfusionNetwork()
cn.add(0.99, DialogueActItem(dai="bye()"))
print cn
pdm.da_in(cn)
pdm.da_out()
def get_config():
global cfg
cfg = Config.load_configs(['../demos/ptien/simulator.cfg', '../demos/ptien/ptien_metadata.py'], log=False)
parser_b.add_argument(
'reference',
help=
'Key value file: Keys contain paths to wav files. Values are reference transcriptions.'
)
args = parser.parse_args()
if os.path.exists(args.out_dir):
if not args.f:
print "\nThe directory '%s' already exists!\n" % args.out_dir
parser.print_usage()
parser.exit()
else:
# create the dir
try:
os.makedirs(args.out_dir)
except OSError as exc:
if exc.errno != errno.EEXIST or os.path.isdir(args.out_dir):
raise exc
cfg = Config.load_configs(args.configs, use_default=True)
asr = asr_factory(cfg)
if args.command == 'extract':
extract_from_xml(args.indomain_data_dir, args.out_dir, cfg)
elif args.command == 'load':
decode_with_reference(args.reference, args.out_dir, args.num_workers)
else:
raise Exception('Argparse mechanism failed: Should never happen')
'as confnets.'))
arger.add_argument('dirname',
help='directory name where to search for WAVs; in '
'fact, it can be path towards a file listing '
'paths to the files in question or path globs or '
'paths to their immediate parent directories')
arger.add_argument('outfname', help='path towards the output file')
arger.add_argument('-c', '--configs', nargs='+',
help='configuration files',
required=True)
arger.add_argument('-s', '--skip', type=int,
help="how many wavs to skip")
arger.add_argument('-g', '--ignore',
type=argparse.FileType('r'),
metavar='FILE',
help='Path towards a file listing globs of CUED '
'call log files that should be ignored.\n'
'The globs are interpreted wrt. the current '
'working directory. For an example, see the '
'source code.')
args = arger.parse_args()
cfg = Config.load_configs(args.configs, log=False)
try:
DEBUG = cfg['General']['debug']
except KeyError:
pass
main(args.dirname, args.outfname, cfg, args.skip, args.ignore)
def setUp(self):
cfg = Config.load_configs()
cfg.config['ASR']['Julius']['msg_timeout'] = 5.
cfg.config['ASR']['Julius']['timeout'] = 5.
cfg.config['corpustools']['get_jasr_confnets']['rt_ratio'] = 0.
self.cfg = cfg
def get_config():
global cfg
cfg = Config.load_configs(['../applications/PublicTransportInfoEN/ptien.cfg'])#, '../applications/PublicTransportInfoEN/ptien_hdc_slu.cfg'])
cfg['Logging']['system_logger'].info("Voip Hub\n" + "=" * 120)
print
text = 'Hello. Thank you for calling. '
voice = 'kal'
print "Synthesize text:", text
print "Voice: ", voice
print
c = {
'TTS': {
'Flite': {
'debug': False,
'voice': 'kal'
}
}
}
cfg = Config.load_configs(log=False)
cfg.update(c)
tts = FliteTTS(cfg)
print 'calling TTS'
wav = tts.synthesize(text)
print 'saving the TTS audio in ./tmp/flite_tts.wav'
audio.save_wav(cfg, './tmp/flite_tts.wav', wav)
print 'playing audio'
audio.play(cfg, wav)
def get_config():
global config
config = Config.load_configs(['config_gp_sarsa.py'], log=False)
('../resources/private/mturk.cfg') and any additional config files passed as
an argument of a '-c'. The additional config file overwrites any
default or previous values.
Remember that the "private" directory is not distributed and it contains
mainly information that you do not want to share.
""")
parser.add_argument('-c',
"--configs",
nargs='+',
help='additional configuration files')
args = parser.parse_args()
mturk_cfg_fname = as_project_path('resources/private/mturk.cfg')
cfg = Config.load_configs([mturk_cfg_fname] + args.configs, log=False)
print "Expire all HITs"
conn = MTurkConnection(
aws_access_key_id=cfg['MTURK']['aws_access_key_id'],
aws_secret_access_key=cfg['MTURK']['aws_secret_access_key'],
host=cfg['MTURK']['host'])
for pnum in range(1, 50):
for hit in conn.search_hits(page_size=100, page_number=pnum):
print "HITId:", hit.HITId
hitStatus = defaultdict(int)
for ass in conn.get_assignments(hit.HITId,
status='Submitted',
help='directory name where to search for WAVs; in '
'fact, it can be path towards a file listing '
'paths to the files in question or path globs or '
'paths to their immediate parent directories')
arger.add_argument('outfname', help='path towards the output file')
arger.add_argument('-c',
'--configs',
nargs='+',
help='configuration files',
required=True)
arger.add_argument('-s', '--skip', type=int, help="how many wavs to skip")
arger.add_argument('-g',
'--ignore',
type=argparse.FileType('r'),
metavar='FILE',
help='Path towards a file listing globs of CUED '
'call log files that should be ignored.\n'
'The globs are interpreted wrt. the current '
'working directory. For an example, see the '
'source code.')
args = arger.parse_args()
cfg = Config.load_configs(args.configs, log=False)
try:
DEBUG = cfg['General']['debug']
except KeyError:
pass
main(args.dirname, args.outfname, cfg, args.skip, args.ignore)
def setUp(self):
cfg = Config.load_configs()
cfg.config['ASR']['Julius']['msg_timeout'] = 5.
cfg.config['ASR']['Julius']['timeout'] = 5.
cfg.config['corpustools']['get_jasr_confnets']['rt_ratio'] = 0.
self.cfg = cfg
def get_config():
global cfg
cfg = Config.load_configs(['scheduler_simulator.cfg'], log=False)
def main():
cldb = CategoryLabelDatabase('../data/database.py')
preprocessing = PTIENSLUPreprocessing(cldb)
slu = PTIENHDCSLU(preprocessing, cfg={'SLU': {PTIENHDCSLU: {'utt2da': as_project_path("applications/PublicTransportInfoEN/data/utt2da_dict.txt")}}})
cfg = Config.load_configs(['../kaldi.cfg',], use_default=True)
asr_rec = asr_factory(cfg)
fn_uniq_trn = 'uniq.trn'
fn_uniq_trn_hdc_sem = 'uniq.trn.hdc.sem'
fn_uniq_trn_sem = 'uniq.trn.sem'
fn_all_sem = 'all.sem'
fn_all_trn = 'all.trn'
fn_all_trn_hdc_sem = 'all.trn.hdc.sem'
fn_all_asr = 'all.asr'
fn_all_asr_hdc_sem = 'all.asr.hdc.sem'
fn_all_nbl = 'all.nbl'
fn_all_nbl_hdc_sem = 'all.nbl.hdc.sem'
fn_train_sem = 'train.sem'
fn_train_trn = 'train.trn'
fn_train_trn_hdc_sem = 'train.trn.hdc.sem'
fn_train_asr = 'train.asr'
fn_train_asr_hdc_sem = 'train.asr.hdc.sem'
fn_train_nbl = 'train.nbl'
fn_train_nbl_hdc_sem = 'train.nbl.hdc.sem'
fn_dev_sem = 'dev.sem'
fn_dev_trn = 'dev.trn'
fn_dev_trn_hdc_sem = 'dev.trn.hdc.sem'
fn_dev_asr = 'dev.asr'
fn_dev_asr_hdc_sem = 'dev.asr.hdc.sem'
fn_dev_nbl = 'dev.nbl'
fn_dev_nbl_hdc_sem = 'dev.nbl.hdc.sem'
fn_test_sem = 'test.sem'
fn_test_trn = 'test.trn'
fn_test_trn_hdc_sem = 'test.trn.hdc.sem'
fn_test_asr = 'test.asr'
fn_test_asr_hdc_sem = 'test.asr.hdc.sem'
fn_test_nbl = 'test.nbl'
fn_test_nbl_hdc_sem = 'test.nbl.hdc.sem'
indomain_data_dir = "indomain_data"
print "Generating the SLU train and test data"
print "-"*120
###############################################################################################
files = []
files.append(glob.glob(os.path.join(indomain_data_dir, 'asr_transcribed.xml')))
files.append(glob.glob(os.path.join(indomain_data_dir, '*', 'asr_transcribed.xml')))
files.append(glob.glob(os.path.join(indomain_data_dir, '*', '*', 'asr_transcribed.xml')))
files.append(glob.glob(os.path.join(indomain_data_dir, '*', '*', '*', 'asr_transcribed.xml')))
files.append(glob.glob(os.path.join(indomain_data_dir, '*', '*', '*', '*', 'asr_transcribed.xml')))
files.append(glob.glob(os.path.join(indomain_data_dir, '*', '*', '*', '*', '*', 'asr_transcribed.xml')))
files = various.flatten(files)
sem = []
trn = []
trn_hdc_sem = []
asr = []
asr_hdc_sem = []
nbl = []
nbl_hdc_sem = []
for fn in files[:100000]:
f_dir = os.path.dirname(fn)
print "Processing:", fn
doc = xml.dom.minidom.parse(fn)
turns = doc.getElementsByTagName("turn")
for i, turn in enumerate(turns):
if turn.getAttribute('speaker') != 'user':
continue
recs = turn.getElementsByTagName("rec")
trans = turn.getElementsByTagName("asr_transcription")
asrs = turn.getElementsByTagName("asr")
if len(recs) != 1:
print "Skipping a turn {turn} in file: {fn} - recs: {recs}".format(turn=i,fn=fn, recs=len(recs))
continue
if len(asrs) == 0 and (i + 1) < len(turns):
next_asrs = turns[i+1].getElementsByTagName("asr")
if len(next_asrs) != 2:
print "Skipping a turn {turn} in file: {fn} - asrs: {asrs} - next_asrs: {next_asrs}".format(turn=i, fn=fn, asrs=len(asrs), next_asrs=len(next_asrs))
continue
print "Recovered from missing ASR output by using a delayed ASR output from the following turn of turn {turn}. File: {fn} - next_asrs: {asrs}".format(turn=i, fn=fn, asrs=len(next_asrs))
hyps = next_asrs[0].getElementsByTagName("hypothesis")
elif len(asrs) == 1:
hyps = asrs[0].getElementsByTagName("hypothesis")
elif len(asrs) == 2:
print "Recovered from EXTRA ASR outputs by using a the last ASR output from the turn. File: {fn} - asrs: {asrs}".format(fn=fn, asrs=len(asrs))
hyps = asrs[-1].getElementsByTagName("hypothesis")
else:
print "Skipping a turn {turn} in file {fn} - asrs: {asrs}".format(turn=i,fn=fn, asrs=len(asrs))
continue
if len(trans) == 0:
print "Skipping a turn in {fn} - trans: {trans}".format(fn=fn, trans=len(trans))
continue
wav_key = recs[0].getAttribute('fname')
wav_path = os.path.join(f_dir, wav_key)
# FIXME: Check whether the last transcription is really the best! FJ
t = various.get_text_from_xml_node(trans[-1])
t = normalise_text(t)
if '--asr-log' not in sys.argv:
asr_rec_nbl = asr_rec.rec_wav_file(wav_path)
a = unicode(asr_rec_nbl.get_best())
else:
a = various.get_text_from_xml_node(hyps[0])
a = normalise_semi_words(a)
if exclude_slu(t) or 'DOM Element:' in a:
print "Skipping transcription:", unicode(t)
print "Skipping ASR output: ", unicode(a)
continue
# The silence does not have a label in the language model.
t = t.replace('_SIL_','')
trn.append((wav_key, t))
print "Parsing transcription:", unicode(t)
print " ASR:", unicode(a)
# HDC SLU on transcription
s = slu.parse_1_best({'utt':Utterance(t)}).get_best_da()
trn_hdc_sem.append((wav_key, s))
if '--uniq' not in sys.argv:
# HDC SLU on 1 best ASR
if '--asr-log' not in sys.argv:
a = unicode(asr_rec_nbl.get_best())
else:
a = various.get_text_from_xml_node(hyps[0])
a = normalise_semi_words(a)
asr.append((wav_key, a))
s = slu.parse_1_best({'utt':Utterance(a)}).get_best_da()
asr_hdc_sem.append((wav_key, s))
# HDC SLU on N best ASR
n = UtteranceNBList()
if '--asr-log' not in sys.argv:
n = asr_rec_nbl
print 'ASR RECOGNITION NBLIST\n',unicode(n)
else:
for h in hyps:
txt = various.get_text_from_xml_node(h)
txt = normalise_semi_words(txt)
n.add(abs(float(h.getAttribute('p'))),Utterance(txt))
n.merge()
n.normalise()
nbl.append((wav_key, n.serialise()))
if '--fast' not in sys.argv:
s = slu.parse_nblist({'utt_nbl':n}).get_best_da()
nbl_hdc_sem.append((wav_key, s))
# there is no manual semantics in the transcriptions yet
sem.append((wav_key, None))
uniq_trn = {}
uniq_trn_hdc_sem = {}
uniq_trn_sem = {}
trn_set = set()
sem = dict(trn_hdc_sem)
for k, v in trn:
if not v in trn_set:
trn_set.add(v)
uniq_trn[k] = v
uniq_trn_hdc_sem[k] = sem[k]
uniq_trn_sem[k] = v + " <=> " + unicode(sem[k])
save_wavaskey(fn_uniq_trn, uniq_trn)
save_wavaskey(fn_uniq_trn_hdc_sem, uniq_trn_hdc_sem, trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
save_wavaskey(fn_uniq_trn_sem, uniq_trn_sem)
# all
save_wavaskey(fn_all_trn, dict(trn))
save_wavaskey(fn_all_trn_hdc_sem, dict(trn_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
if '--uniq' not in sys.argv:
save_wavaskey(fn_all_asr, dict(asr))
save_wavaskey(fn_all_asr_hdc_sem, dict(asr_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
save_wavaskey(fn_all_nbl, dict(nbl))
save_wavaskey(fn_all_nbl_hdc_sem, dict(nbl_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
seed_value = 10
random.seed(seed_value)
random.shuffle(trn)
random.seed(seed_value)
random.shuffle(trn_hdc_sem)
random.seed(seed_value)
random.shuffle(asr)
random.seed(seed_value)
random.shuffle(asr_hdc_sem)
random.seed(seed_value)
random.shuffle(nbl)
random.seed(seed_value)
random.shuffle(nbl_hdc_sem)
# trn
train_trn = trn[:int(0.8*len(trn))]
dev_trn = trn[int(0.8*len(trn)):int(0.9*len(trn))]
test_trn = trn[int(0.9*len(trn)):]
save_wavaskey(fn_train_trn, dict(train_trn))
save_wavaskey(fn_dev_trn, dict(dev_trn))
save_wavaskey(fn_test_trn, dict(test_trn))
# trn_hdc_sem
train_trn_hdc_sem = trn_hdc_sem[:int(0.8*len(trn_hdc_sem))]
dev_trn_hdc_sem = trn_hdc_sem[int(0.8*len(trn_hdc_sem)):int(0.9*len(trn_hdc_sem))]
test_trn_hdc_sem = trn_hdc_sem[int(0.9*len(trn_hdc_sem)):]
save_wavaskey(fn_train_trn_hdc_sem, dict(train_trn_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
save_wavaskey(fn_dev_trn_hdc_sem, dict(dev_trn_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
save_wavaskey(fn_test_trn_hdc_sem, dict(test_trn_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
# asr
train_asr = asr[:int(0.8*len(asr))]
dev_asr = asr[int(0.8*len(asr)):int(0.9*len(asr))]
test_asr = asr[int(0.9*len(asr)):]
save_wavaskey(fn_train_asr, dict(train_asr))
save_wavaskey(fn_dev_asr, dict(dev_asr))
save_wavaskey(fn_test_asr, dict(test_asr))
# asr_hdc_sem
train_asr_hdc_sem = asr_hdc_sem[:int(0.8*len(asr_hdc_sem))]
dev_asr_hdc_sem = asr_hdc_sem[int(0.8*len(asr_hdc_sem)):int(0.9*len(asr_hdc_sem))]
test_asr_hdc_sem = asr_hdc_sem[int(0.9*len(asr_hdc_sem)):]
save_wavaskey(fn_train_asr_hdc_sem, dict(train_asr_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
save_wavaskey(fn_dev_asr_hdc_sem, dict(dev_asr_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
save_wavaskey(fn_test_asr_hdc_sem, dict(test_asr_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
# n-best lists
train_nbl = nbl[:int(0.8*len(nbl))]
dev_nbl = nbl[int(0.8*len(nbl)):int(0.9*len(nbl))]
test_nbl = nbl[int(0.9*len(nbl)):]
save_wavaskey(fn_train_nbl, dict(train_nbl))
save_wavaskey(fn_dev_nbl, dict(dev_nbl))
save_wavaskey(fn_test_nbl, dict(test_nbl))
# nbl_hdc_sem
train_nbl_hdc_sem = nbl_hdc_sem[:int(0.8*len(nbl_hdc_sem))]
dev_nbl_hdc_sem = nbl_hdc_sem[int(0.8*len(nbl_hdc_sem)):int(0.9*len(nbl_hdc_sem))]
test_nbl_hdc_sem = nbl_hdc_sem[int(0.9*len(nbl_hdc_sem)):]
save_wavaskey(fn_train_nbl_hdc_sem, dict(train_nbl_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
save_wavaskey(fn_dev_nbl_hdc_sem, dict(dev_nbl_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
save_wavaskey(fn_test_nbl_hdc_sem, dict(test_nbl_hdc_sem), trans = lambda da: '&'.join(sorted(unicode(da).split('&'))))
cldb = CategoryLabelDatabase('../data/database.py')
preprocessing = PTICSSLUPreprocessing(cldb)
slu = PTICSHDCSLU(
preprocessing,
cfg={
'SLU': {
PTICSHDCSLU: {
'utt2da':
as_project_path(
"applications/PublicTransportInfoCS/data/utt2da_dict.txt")
}
}
})
cfg = Config.load_configs([
'../kaldi.cfg',
], use_default=True)
asr_rec = asr_factory(cfg)
def normalise_semi_words(txt):
# normalise these semi-words
if txt == '__other__':
txt = '_other_'
elif txt == '__silence__':
txt = '_other_'
elif not txt:
txt = '_other_'
return txt
if __name__ == '__main__':
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
Switchboard system records conversation between two users.
When the first user calls the system, the systems rejects the call. Then in a few seconds,
it calls back to the first user, informs about how to use the system and the recording data.
Then, it asks the first user to enter a phone number of a second user. If the number is entered successfully,
it calls the second user.
The systems calls back to the user to prevent any call charges on the users' side.
The program reads the default config in the resources directory ('../resources/default.cfg').
In addition, it reads all config file passed as an argument of a '-c'.
The additional config files overwrites any default or previous values.
""")
parser.add_argument('-o', action="store", dest="caller", nargs='+', help='additional configure file')
parser.add_argument('-d', action="store", dest="callee", nargs='+', help='additional configure file')
args = parser.parse_args()
cfg1 = Config.load_configs(args.caller)
cfg2 = Config.load_configs(args.callee)
run(cfg1, cfg2)
parser = argparse.ArgumentParser(
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
Gets account balance at MTURK.
The program reads the default config in the resources directory
('../resources/private/mturk.cfg') and any additional config files passed as
an argument of a '-c'. The additional config file overwrites any
default or previous values.
Remember that the "private" directory is not distributed and it contains
mainly information that you do not want to share.
""")
parser.add_argument('-c', "--configs", nargs='+',
help='additional configuration files')
args = parser.parse_args()
mturk_cfg_fname = as_project_path('resources/private/mturk.cfg')
cfg = Config.load_configs([mturk_cfg_fname] + args.configs, log=False)
print "Gets MTURK account balance"
print "-" * 120
print
conn = MTurkConnection(aws_access_key_id = cfg['MTURK']['aws_access_key_id'],
aws_secret_access_key = cfg['MTURK']['aws_secret_access_key'],
host = cfg['MTURK']['host'])
print "Account balance:", conn.get_account_balance()
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")
test_vio.py tests the VoipIO component.
The program reads the default config in the resources directory
('../resources/default.cfg') and any additional config files passed as
an argument of a '-c'. The additional config file overwrites any
default or previous values.
""")
parser.add_argument('-c',
"--configs",
nargs='+',
help='additional configuration files')
args = parser.parse_args()
cfg = Config.load_configs(args.configs)
session_logger = cfg['Logging']['session_logger']
system_logger = cfg['Logging']['system_logger']
#########################################################################
#########################################################################
system_logger.info("Test of the VoipIO component\n" + "=" * 120)
vio_commands, vio_child_commands = multiprocessing.Pipe()
# used to send commands to VoipIO
vio_record, vio_child_record = multiprocessing.Pipe()
# I read from this connection recorded audio
vio_play, vio_child_play = multiprocessing.Pipe()
def setUp(self):
self.cfg = Config.load_configs(config=CONFIG_DICT, use_default=False,
log=False)
def setUp(self):
self.cfg = Config.load_configs(config=CONFIG_DICT,
use_default=False,
log=False)
def get_config():
global cfg
cfg = Config.load_configs(['config_asr_simulator.py'], log=False)
print "Language: ", language
print
c = {
'TTS': {
'Google': {
'debug':
False,
'preprocessing':
as_project_path("resources/tts/prep_speechtech_en.cfg"),
'tempo':
1.0,
'language':
language
}
}
}
cfg = Config.load_configs(log=False)
cfg.update(c)
tts = GoogleTTS(cfg)
print 'calling TTS'
wav = tts.synthesize(text)
print 'saving the TTS audio in ./tmp/google_tts.wav'
audio.save_wav(cfg, './tmp/google_tts.wav', wav)
print 'playing audio'
audio.play(cfg, wav)
parser_a.add_argument('indomain_data_dir',
help='Directory which should contain symlinks or directories with transcribed ASR')
parser_b = subparsers.add_parser(
'load', help='Load wav transcriptions and reference with full paths to wavs')
parser_b.add_argument(
'reference', help='Key value file: Keys contain paths to wav files. Values are reference transcriptions.')
args = parser.parse_args()
if os.path.exists(args.out_dir):
if not args.f:
print "\nThe directory '%s' already exists!\n" % args.out_dir
parser.print_usage()
parser.exit()
else:
# create the dir
try:
os.makedirs(args.out_dir)
except OSError as exc:
if exc.errno != errno.EEXIST or os.path.isdir(args.out_dir):
raise exc
cfg = Config.load_configs(args.configs, use_default=True)
if args.command == 'extract':
extract_from_xml(args.indomain_data_dir, args.out_dir, cfg)
elif args.command == 'load':
decode_with_reference(args.reference, args.out_dir, cfg)
else:
raise Exception('Argparse mechanism failed: Should never happen')
formatter_class=argparse.RawDescriptionHelpFormatter,
description="""
test_vio.py tests the VoipIO component.
The program reads the default config in the resources directory
('../resources/default.cfg') and any additional config files passed as
an argument of a '-c'. The additional config file overwrites any
default or previous values.
""")
parser.add_argument('-c', "--configs", nargs='+',
help='additional configuration files')
args = parser.parse_args()
cfg = Config.load_configs(args.configs)
session_logger = cfg['Logging']['session_logger']
system_logger = cfg['Logging']['system_logger']
#########################################################################
#########################################################################
system_logger.info("Test of the AudioIO component\n" + "=" * 120)
wav = audio.load_wav(cfg, './resources/test16k-mono.wav')
# split audio into frames
wav = various.split_to_bins(wav, 2 * cfg['Audio']['samples_per_frame'])
# remove the last frame
aio_commands, aio_child_commands = multiprocessing.Pipe() # used to send aio_commands
audio_record, child_audio_record = multiprocessing.Pipe() # I read from this connection recorded audio
""" The script has commands:
--asr-log it uses the asr hypotheses from call logs
"""
asr_log = 0
num_workers = 1
cldb = CategoryLabelDatabase('../data/database.py')
preprocessing = PTICSSLUPreprocessing(cldb)
slu = PTICSHDCSLU(preprocessing, cfg = {'SLU': {PTICSHDCSLU: {'utt2da': as_project_path("applications/PublicTransportInfoCS/data/utt2da_dict.txt")}}})
cfg = Config.load_configs(['../kaldi.cfg',], use_default=True)
asr_rec = asr_factory(cfg)
def normalise_semi_words(txt):
# normalise these semi-words
if txt == '__other__':
txt = '_other_'
elif txt == '__silence__':
txt = '_other_'
elif not txt:
txt = '_other_'
return txt
def process_call_log(fn):
name = multiprocessing.current_process().name