OpenSesame voicekey

voicekey.py

import pyaudio
import wave
import sys
import struct
import math 

TAP_THRESHOLD = 0.050
FORMAT = pyaudio.paInt16 
SHORT_NORMALIZE = (1.0/32768.0)
CHANNELS = 2
RATE = 44100  
INPUT_BLOCK_TIME = 0.01
INPUT_FRAMES_PER_BLOCK = int(RATE*INPUT_BLOCK_TIME)
chunk=1024

def get_rms(block):

	"""Get root mean square as a measure of loudness"""

	count = len(block)/2
	format = "%dh" % (count)
	shorts = struct.unpack( format, block )
	sum_squares = 0.0
	for sample in shorts:
		n = sample * SHORT_NORMALIZE
		sum_squares += n*n
	return math.sqrt( sum_squares / count )

# Open the mic
stream = pyaudio.PyAudio().open(
	format=FORMAT,
	channels=CHANNELS,
	rate=RATE,
	input=True,
	input_device_index=0,
	frames_per_buffer=INPUT_FRAMES_PER_BLOCK
	)

# Listen until a sound has been detected
start_response_interval = self.time()
end_response_interval = None
trial_duration = 4000
while self.time() - start_response_interval < trial_duration:
	try:
		block = stream.read(chunk)
		all.append(block)
	except IOError as e:
		print e
	loudness = get_rms( block )
	if loudness > TAP_THRESHOLD:
		end_response_interval = self.time()
		response_loudness = loudness
if end_response_interval is None:
	set_response(response='timeout', response_time=None)
	var.loudness = "timeout"
else:
	rt = end_response_interval - start_response_interval
	set_response(response='detected', response_time=rt)
	var.loudness = response_loudness

stream.close()
pyaudio.PyAudio().terminate()