record.py

"""INITIAL CODE FROM: https://stackoverflow.com/questions/892199/detect-record-audio-in-python"""


from sys import byteorder
from array import array
from struct import pack
import pyaudio
import signal
import wave

THRESHOLD = 1100
CHUNK_SIZE = 1024
FORMAT = pyaudio.paInt16
RATE = 16000
AMOUNT_OF_SILENCE = 15 # represents an arbitrary unit. the greater this value, the "longer" period of constant silence is required before the recording stops
def is_silent(snd_data):
    "Returns 'True' if below the 'silent' threshold"
    return max(snd_data) < THRESHOLD

def normalize(snd_data):
    "Average the volume out"
    MAXIMUM = 16384
    times = float(MAXIMUM)/max(abs(i) for i in snd_data)

    r = array('h')
    for i in snd_data:
        r.append(int(i*times))
    return r

def trim(snd_data):
    "Trim the blank spots at the start and end"
    def _trim(snd_data):
        snd_started = False
        r = array('h')

        for i in snd_data:
            if not snd_started and abs(i)>THRESHOLD:
                snd_started = True
                r.append(i)

            elif snd_started:
                r.append(i)
        return r

    # Trim to the left
    snd_data = _trim(snd_data)

    # Trim to the right
    snd_data.reverse()
    snd_data = _trim(snd_data)
    snd_data.reverse()
    return snd_data

def add_silence(snd_data, seconds):
    "Add silence to the start and end of 'snd_data' of length 'seconds' (float)"
    r = array('h', [0 for i in xrange(int(seconds*RATE))])
    r.extend(snd_data)
    r.extend([0 for i in xrange(int(seconds*RATE))])
    return r

def record():
    """
    Record a word or words from the microphone and 
    return the data as an array of signed shorts.

    Normalizes the audio, trims silence from the 
    start and end, and pads with 0.5 seconds of 
    blank sound to make sure VLC et al can play 
    it without getting chopped off.
    """
    p = pyaudio.PyAudio()
    stream = p.open(format=FORMAT, channels=1, rate=RATE,
        input=True, output=True,
        frames_per_buffer=CHUNK_SIZE)
    num_silent = 0
    snd_started = False # if true, the recording will not wait for the user to start talking
    
    # handle the user force closing the script without the required amount of silence
    global interrupted 
    interrupted = False 
    def interrupt_handler(signal, frame):
        global interrupted 
        interrupted = True
    signal.signal(signal.SIGINT, interrupt_handler)

    r = array('h')

    while 1:
        # little endian, signed short
        snd_data = array('h', stream.read(CHUNK_SIZE))
        if byteorder == 'big':
            snd_data.byteswap()
        r.extend(snd_data)

        silent = is_silent(snd_data)

        if silent and snd_started:
            num_silent += 1 # leaky bucket
        elif not silent and snd_started:
            if num_silent > 0:
                num_silent -= 1 # leaky bucket
        elif not silent and not snd_started:
            print("User started to speak")
            snd_started = True
        if (snd_started and num_silent > AMOUNT_OF_SILENCE) or interrupted:
            break

    sample_width = p.get_sample_size(FORMAT)
    stream.stop_stream()
    stream.close()
    p.terminate()

    r = normalize(r)
    r = trim(r)
    r = add_silence(r, 0.5)
    return sample_width, r

def record_to_file(path):
    "Records from the microphone and outputs the resulting data to 'path'"
    sample_width, data = record()
    data = pack('<' + ('h'*len(data)), *data)

    wf = wave.open(path, 'wb')
    wf.setnchannels(1)
    wf.setsampwidth(sample_width)
    wf.setframerate(RATE)
    wf.writeframes(data)
    print("Done recording")
    return (data, wf)

def start_recording():
    return record_to_file('./inputs/raw_recording.wav') # returns raw data AND OPEN wave file
if __name__ == "__main__":
    start_recording()