Speech Recognition Thread

speechThread.py

# Speech Recognition Thread identifies the command from defined synonyms and inserting to stt Queue
def stopStream(stream_reader):

    if stream_reader:
        stream_reader.stop_stream()
        stream_reader = None

def received_frames(frames, speech, stt):

    speech.push_data(frames, finish_processing=False)
    utt_text, is_stable = speech.get_result()
    rh_result = utt_text.decode("utf-8").strip().lower()

    if (len(rh_result) > 0):
        stt.put(rh_result)

def load_device():
    """Reload audio device list"""
    device_list, default_input_index, loopback_index = \
                                audio_helper.get_input_device_list()
    if not device_list:
        print("No audio devices available")

    return device_list

# Function to search for match with any of the defined synonyms of each command
def detectSoundEvent(utterance, controls, control_syn):

    utters = utterance.split(' ')[-3:]
    utters.reverse()
    print(utters)

    for utter in  utters:
        for control in controls:
            synonyms = control_syn.get(control)
            for synonym in synonyms:
                if synonym in utter:
                    print('Event Trigger: ' + control)
                    return control, utters[-1]

    return None, utters[0] #last word will return as reversed
    

    #####################################################################  
    # Initializing the Speech Recognition Thread
    #####################################################################  

    # You can add more controls as you deem fit.
    numbers = ['zero', 'one', 'two', 'three', 'four', \
                'five', 'six', 'seven', 'eight', 'nine']

    controls = ['left', 'right', 'up', 'down']

    control_syn = {}
    for control in controls:
        control_syn.setdefault(control, [])

    # Need to account for similar sounding words as speech recog is on the edge!
    control_syn['left'].extend(['let', 'left', 'light', 'live', 'laugh'])
    control_syn['right'].extend(['right', 'write', 'great', 'fight', 'might', 'ride'])
    control_syn['up'].extend(['up', 'hop', 'hope', 'out'])
    control_syn['down'].extend(['down', 'doubt', 'though'])

    device_list = load_device()

    stream_reader = audio_helper.StreamReader(
                        device_list[1][0], received_frames)

    if not stream_reader.initialize():
            print("Failed to initialize Stream Reader")
            speech.close()
            speech = None
            return

    speech = SpeechManager()
    print('speech config = ' + str(SPEECH_CONFIG))
    if not speech.initialize(SPEECH_CONFIG,
            infer_device='CPU',
            batch_size=8):
        print("Failed to initialize ASR recognizer")
        speech.close()
        speech = None
        return

    stt = Queue()
    prevUtterance = ''

    reading_thread = Thread(target=stream_reader.read_stream, \
                        args=(speech, stt), daemon=True)
    reading_thread.start()