def task(quit_event):
mic = Microphone(quit_event=quit_event)
bing = BingSpeechAPI(key=BING_KEY)
while not quit_event.is_set():
if mic.wakeup('watson'):
print('Wake up')
os.system('rm temp.mp3')
data = mic.listen()
try:
text = bing.recognize(data)
if text:
print('\n> %s' % text)
if 'play music' in text:
tts = gTTS(text='I will play music!', lang='en-us')
tts.save("temp.mp3")
os.system('madplay temp.mp3')
os.system('madplay ~/Tchaikovsky_Concerto_No.1p.mp3')
else:
output = chat(text)
print('\n>> %s' % output)
tts = gTTS(text=output, lang='en-us')
tts.save("temp.mp3")
os.system('madplay temp.mp3')
except Exception as e:
print(e.message)
def __init__(self, key):
super(Bing, self).__init__()
self.key = key
self.queue = queue.Queue()
self.listening = False
self.done = False
self.event = threading.Event()
self.bing = BingSpeechAPI(BING_KEY)
def bing_init(self):
text = ""
bing = BingSpeechAPI(key=BING_KEY)
try:
fd = open(self.path)
conect = fd.read(-1)
text = bing.recognize(conect)
fd.close()
return text
except Exception as e:
print(e.message)
return text
def task(quit_event):
mic = Microphone(quit_event=quit_event)
bing = BingSpeechAPI(key=BING_KEY)
while not quit_event.is_set():
if mic.wakeup('respeaker'):
print('Wake up')
data = mic.listen()
try:
text = bing.recognize(data)
if text:
print(('Recognized %s' % text))
except Exception as e:
print((e.message))
def task(quit_event):
mic = Microphone(quit_event=quit_event)
bing = BingSpeechAPI(key=BING_KEY)
while not quit_event.is_set():
if mic.wakeup('respeaker'):
print('Wake up')
data = mic.listen()
try:
text = bing.recognize(data)
if text:
print('Recognized %s' % text)
if 'play music' in text:
print('I will play music!')
os.system('madplay Tchaikovsky_Concerto_No.1p.mp3')
except Exception as e:
print(e.message)
def bing__parse_speech(self):
bing = BingSpeechAPI(key=BING_KEY)
try:
fd = open(self.path)
conect = fd.read(-1)
text = bing.recognize(conect)
fd.close()
if text:
print('Recognized %s' % text)
#f = open("out.txt", "w")
#print >> f, "%s " % (text)
#f.close()
#print(strlen)
#print(str_doc[0:strlen])
convert_lis = convert_to_list()
#print("******12*********")
find_name = fuzzyfinder(text,convert_lis)
#print("***************")
#print(find_name)
#print("******1*********")
ret_phonenumber = search_user_en(''.join(find_name).lower())
#print("************************")
#print(ret_phonenumber)
if ret_phonenumber:
global is_callflags
is_callflags = True
c_serial.serial_send(gfd,11,ret_phonenumber);
print("************************")
else:
play_call_error_audio()
return 0
else:
print('Recognized error %s' % text)
return -1
except Exception as e:
print(e.message)
'''
def convert(audio_data):
if isinstance(audio_data, types.GeneratorType):
def generate(audio):
yield BingSpeechAPI.get_wav_header()
for a in audio:
yield a
data = generate(audio_data)
else:
data = BingSpeechAPI.to_wav(audio_data)
audio = sr.AudioData(''.join(data), 16000, 2)
return audio
def generate(audio):
yield BingSpeechAPI.get_wav_header()
for a in audio:
yield a
class Bing(Element):
def __init__(self, key):
super(Bing, self).__init__()
self.key = key
self.queue = queue.Queue()
self.listening = False
self.done = False
self.event = threading.Event()
self.bing = BingSpeechAPI(BING_KEY)
def put(self, data):
if self.listening:
self.queue.put(data)
def start(self):
self.done = False
thread = threading.Thread(target=self.run)
thread.daemon = True
thread.start()
def stop(self):
self.done = True
def listen(self):
self.listening = True
self.event.set()
def run(self):
while not self.done:
self.event.wait()
def gen():
count = 0
while count < 16000 * 6:
data = self.queue.get()
if not data:
break
yield data
count += len(data) / 2
#recognize speech using Microsoft Bing Voice Recognition
try:
# text = bing.recognize(gen(), language='zh-CN')
text = self.bing.recognize(gen())
global stringcopy
print('Bing:{}'.format(text).encode('utf-8'))
stringcopy = format(text).encode('utf-8')
except ValueError:
print('Not recognized')
global is_music
is_music = False
time.sleep(1)
#play_music('mpg123 /home/respeaker/Voice_Reception_System/notfind.mp3')
play_music(
'mpg123 /home/respeaker/Voice_Reception_System/not_clear.mp3'
)
except RequestError as e:
print('Network error {}'.format(e))
time.sleep(1)
play_music(
'mpg123 /home/respeaker/Voice_Reception_System/net_error.mp3'
)
self.listening = False
self.event.clear()
self.queue.queue.clear()
global recvok, is_record
recvok = True
is_record = True
from respeaker.bing_speech_api import BingSpeechAPI
from respeaker import pixel_ring
from worker import Worker
import time
try:
from creds import BING_KEY
except ImportError:
print(
'Get a key from https://www.microsoft.com/cognitive-services/en-us/speech-api and create creds.py with the key'
)
sys.exit(-1)
bing = BingSpeechAPI(key=BING_KEY)
mic = Microphone()
player = Player(mic.pyaudio_instance)
myworker = Worker()
myworker.set_tts(bing)
myworker.set_player(player)
mission_completed = False
awake = False
def handle_int(sig, frame):
global mission_completed
def task(quit_event):
mic = Microphone(quit_event=quit_event)
bing = BingSpeechAPI(key=BING_KEY)
while not quit_event.is_set():
if mic.wakeup('lithnet'):
print('Wake up')
os.system('madplay yes-female.mp3')
data = mic.listen()
try:
text = bing.recognize(data)
if text:
print('Converted query from speech: %s' % text)
os.system('madplay LetmehavealookFemale.mp3')
try:
# -----------------------------
# Search MIM for Object
# -----------------------------
params = {}
params['query'] = str(text)
params['staging'] = "true"
headers = {"Content-Type" : "application/x-www-form-urlencoded"}
# Connect to server to get the Access Token
print ("Connect to Azure Function to get Object from MIM")
textresp = httplib.HTTPSConnection("yourAzureFunctionApp.azurewebsites.net")
code = {"code" : "yourAzureFunctionKey=="}
functioncode = urllib.urlencode(code)
textresp.request("POST", "/api/yourAzureFunction?" + functioncode, json.dumps(params), headers)
response = textresp.getresponse()
data = response.read()
print(response.status, response.reason)
# Remove CRLF and leading "
data = data[:-5]
data = data[1:]
print('MIM Returned: ' + data)
returnedResults = json.loads(data)
# -----------------------------
# Convert Repsonse to Speech
# -----------------------------
if data:
mimResponse = returnedResults['MIMResponse']
tokenurl = "https://api.cognitive.microsoft.com/sts/v1.0/issueToken"
ttskey = 'yourAzureTextToSpeechAPIKey'
params = ""
ttstokenheaders = {"Ocp-Apim-Subscription-Key": ttskey}
print("Getting AccessToken from westus.tts.speech.microsoft.com for Text to Speech Conversion")
resp = requests.post(tokenurl, params=params, headers=ttstokenheaders)
token = resp.text
accesstoken = token.decode("UTF-8")
ttsurl = 'https://westus.tts.speech.microsoft.com/cognitiveservices/v1'
ttsheaders = {}
ttsheaders['Ocp-Apim-Subscription-Key'] = ttskey
ttsheaders['Content-Type'] = "application/ssml+xml"
ttsheaders['X-Microsoft-OutputFormat'] = "audio-16khz-32kbitrate-mono-mp3"
ttsheaders['User-Agent'] = "MIMText2Speech"
ttsheaders['Authorization'] = "Bearer " + accesstoken
#<speak version='1.0' xmlns="http://www.w3.org/2001/10/synthesis" xml:lang='en-US'><voice name='Microsoft Server Speech Text to Speech Voice (en-AU, HayleyRUS)'><prosody volume="+20.00%">Welcome to use Microsoft Cognitive Services Text-to-Speech API.</prosody></voice> </speak>
body = ElementTree.Element('speak', version='1.0')
body.set('{http://www.w3.org/XML/1998/namespace}lang', 'en-us')
voice = ElementTree.SubElement(body, 'voice')
voice.set('{http://www.w3.org/XML/1998/namespace}lang', 'en-AU')
voice.set('{http://www.w3.org/XML/1998/namespace}gender', 'Female')
voice.set('name', 'Microsoft Server Speech Text to Speech Voice (en-AU, HayleyRUS)')
prosody = ElementTree.SubElement(body, 'prosody')
prosody.set('volume', '-50.00%')
prosody.set('rate', '-50.00%')
voice.text = data
print("Calling westus.tts.speech.microsoft.com to convert response to audio")
audioresp = httplib.HTTPSConnection("westus.tts.speech.microsoft.com")
audioresp.request("POST", "/cognitiveservices/v1", ElementTree.tostring(body), ttsheaders)
response = audioresp.getresponse()
data = response.read()
print(response.status, response.reason)
file = open("audioout.mp3", "wb")
file.write(data)
file.close()
# Play Response
os.system('madplay audioout.mp3')
# -----------------------------
# Reporting and Auditing
# -----------------------------
datetimenow = strftime("%m-%d-%Y %H:%M:%S", gmtime())
logparams = {}
logparams['deviceId'] = "MIMVoice"
logparams['messageId'] = str(datetimenow)
logparams['messageString'] = "MIMVoice-to-Cloud-" +str(datetimenow)
logparams['MIMQuery'] = str(text)
logparams['MIMResponse'] = mimResponse
logparams['entity'] = returnedResults['fullname']
logparams['entitlement'] = returnedResults['entitlement']
logparams['date'] = strftime("%m-%d-%Y", gmtime())
logheaders = {}
logheaders['Authorization'] = SASToken
logheaders['Content-Type'] = "application/json"
# Send Event to IoT Hub
print ("Sending Event Summary to IoT Hub - " + IoTHubName + ".azure-devices.net from deviceID " + deviceID)
logresp = httplib.HTTPSConnection(IoTHubName + ".azure-devices.net")
logresp.request("POST", "/devices/" + deviceID + "/messages/events?api-version=" + iotHubAPIVer, json.dumps(logparams), logheaders)
logresponse = logresp.getresponse()
logdata = logresponse.read()
if logdata:
print(logresponse.status, logresponse.reason)
logdata = logdata[:-5]
print("DEBUG:Event Summary send to IoT Hub failed: " + logdata)
except Exception as e:
print(e.message)
except Exception as e:
print(e.message)
def task(quit_event):
global ansNum
global isStart
global isChat
global ans
global vocabulary
global score
mic = Microphone(quit_event=quit_event)
bing = BingSpeechAPI(key=BING_KEY)
while not quit_event.is_set():
if mic.wakeup('teresa'):
print('Wake up')
os.system('rm temp.mp3')
data = mic.listen()
try:
text = bing.recognize(data)
if text:
print('\n> %s' % text)
if (isStart == False) and ('test start' in text):
response = requests.get(END_POINT + '/1/vocabulary')
qaObj = response.json()
vocabulary = qaObj["question"]
ans = qaObj["answer"]
score = [4] * len(vocabulary)
isStart = True
vocNo = 0
tts = gTTS(text="How to spell " + vocabulary[vocNo],
lang='en-us')
tts.save("temp.mp3")
os.system('madplay temp.mp3')
elif (isStart == False) and ('play music' in text):
tts = gTTS(text='I will play music!', lang='en-us')
tts.save("temp.mp3")
os.system('madplay temp.mp3')
os.system('madplay ~/Tchaikovsky_Concerto_No.1p.mp3')
elif (isStart
== False) and (isChat == False) and ('chat' in text):
isChat = True
tts = gTTS(text='OK! Let’s Chat !', lang='en-us')
tts.save("temp.mp3")
os.system('madplay temp.mp3')
elif (isStart == False) and (isChat
== True) and ('Stop Chat'
in text):
isChat = False
tts = gTTS(text='So, let’s talk again soon!',
lang='en-us')
tts.save("temp.mp3")
os.system('madplay temp.mp3')
elif (isStart == False) and (isChat == True):
output = chat(text)
print('\n>> %s' % output)
tts = gTTS(text=output, lang='en-us')
tts.save("temp.mp3")
os.system('madplay temp.mp3')
elif isStart == False:
tts = gTTS(
text="Please say test start to start the test.",
lang='en-us')
tts.save("temp.mp3")
os.system('madplay temp.mp3')
else:
output = vocTest(text)
print('\n>> %s' % output)
tts = gTTS(text=output, lang='en-us')
tts.save("temp.mp3")
os.system('madplay temp.mp3')
except Exception as e:
print(e.message)