def __init__(self, wf=None):
"""
wf = None : mic
"""
# Visualizations of result
self.vis = Visualizations()
# network parameter
self.numCols = 2**9 # 2**9 = 512
sparsity = 0.10
self.numInput = int(self.numCols * sparsity)
# encoder of audiostream
self.e = BitmapArrayEncoder(self.numCols, 1)
# setting audio
p = pyaudio.PyAudio()
if wf == None:
self.wf = None
channels = 1
rate = 44100 # sampling周波数: １秒間に44100回
secToRecord = .1 #
self.buffersize = 2**12
self.buffersToRecord=int(rate*secToRecord/self.buffersize)
if not self.buffersToRecord:
self.buffersToRecord = 1
audio_format = pyaudio.paInt32
else:
self.printWaveInfo(wf)
channels = wf.getnchannels()
self.wf = wf
rate = wf.getframerate()
secToRecord = wf.getsampwidth()
self.buffersize = 1024
self.buffersToRecord=int(rate*secToRecord/self.buffersize)
if not self.buffersToRecord:
self.buffersToRecord = 1
audio_format = p.get_format_from_width(secToRecord)
self.inStream = p.open(
format=audio_format,
channels=channels,
rate=rate,
input=True,
output=True,
frames_per_buffer=self.buffersize)
self.audio = numpy.empty((self.buffersToRecord*self.buffersize), dtype="uint32")
# filters in Hertz
# max lowHertz = (buffersize / 2-1) * rate / buffersize
highHertz = 500
lowHertz = 10000
# Convert filters from Hertz to bins
self.highpass = max(int(highHertz * self.buffersize /rate), 1)
self.lowpass = min(int(lowHertz * self.buffersize / rate), self.buffersize/2 -1)
# Temporal Pooler
self.tp = TP(
numberOfCols = self.numCols,
cellsPerColumn = 4,
initialPerm = 0.5,
connectedPerm = 0.5,
minThreshold = 10,
newSynapseCount = 10,
permanenceInc = 0.1,
permanenceDec = 0.07,
activationThreshold = 8,
globalDecay = 0.02,
burnIn = 2,
checkSynapseConsistency = False,
pamLength = 100
)
print("Number of columns: ", str(self.numCols))
print("Max size of input: ", str(self.numInput))
print("Sampling rate(Hz): ", str(rate))
print("Passband filter(Hz): ", str(highHertz), " - ", str(lowHertz))
print("Passband filter(bin):", str(self.highpass), " - ", str(self.lowpass))
print("Bin difference: ", str(self.lowpass - self.highpass))
print("Buffersize: ", str(self.buffersize))
class AudioStream:
def printWaveInfo(self, wf):
"""
WAVEファイルの情報を取得
"""
print()
print("チャンネル数:", wf.getnchannels() )
print("サンプル幅:", wf.getsampwidth() )
print("サンプリング周波数:", wf.getframerate() )
print("フレーム数:", wf.getnframes() )
print("パラメータ:", wf.getparams() )
print("長さ（秒）:", float(wf.getnframes()) / wf.getframerate() )
print()
def __init__(self, wf=None):
"""
wf = None : mic
"""
# Visualizations of result
self.vis = Visualizations()
# network parameter
self.numCols = 2**9 # 2**9 = 512
sparsity = 0.10
self.numInput = int(self.numCols * sparsity)
# encoder of audiostream
self.e = BitmapArrayEncoder(self.numCols, 1)
# setting audio
p = pyaudio.PyAudio()
if wf == None:
self.wf = None
channels = 1
rate = 44100 # sampling周波数: １秒間に44100回
secToRecord = .1 #
self.buffersize = 2**12
self.buffersToRecord=int(rate*secToRecord/self.buffersize)
if not self.buffersToRecord:
self.buffersToRecord = 1
audio_format = pyaudio.paInt32
else:
self.printWaveInfo(wf)
channels = wf.getnchannels()
self.wf = wf
rate = wf.getframerate()
secToRecord = wf.getsampwidth()
self.buffersize = 1024
self.buffersToRecord=int(rate*secToRecord/self.buffersize)
if not self.buffersToRecord:
self.buffersToRecord = 1
audio_format = p.get_format_from_width(secToRecord)
self.inStream = p.open(
format=audio_format,
channels=channels,
rate=rate,
input=True,
output=True,
frames_per_buffer=self.buffersize)
self.audio = numpy.empty((self.buffersToRecord*self.buffersize), dtype="uint32")
# filters in Hertz
# max lowHertz = (buffersize / 2-1) * rate / buffersize
highHertz = 500
lowHertz = 10000
# Convert filters from Hertz to bins
self.highpass = max(int(highHertz * self.buffersize /rate), 1)
self.lowpass = min(int(lowHertz * self.buffersize / rate), self.buffersize/2 -1)
# Temporal Pooler
self.tp = TP(
numberOfCols = self.numCols,
cellsPerColumn = 4,
initialPerm = 0.5,
connectedPerm = 0.5,
minThreshold = 10,
newSynapseCount = 10,
permanenceInc = 0.1,
permanenceDec = 0.07,
activationThreshold = 8,
globalDecay = 0.02,
burnIn = 2,
checkSynapseConsistency = False,
pamLength = 100
)
print("Number of columns: ", str(self.numCols))
print("Max size of input: ", str(self.numInput))
print("Sampling rate(Hz): ", str(rate))
print("Passband filter(Hz): ", str(highHertz), " - ", str(lowHertz))
print("Passband filter(bin):", str(self.highpass), " - ", str(self.lowpass))
print("Bin difference: ", str(self.lowpass - self.highpass))
print("Buffersize: ", str(self.buffersize))
# # setup plot
# plt.ion()
# bin = range(self.highpass, self.lowpass)
# xs = numpy.arange(len(bin)*rate/self.buffersize + highHertz)
# self.freqPlot = plt.plot(xs, xs)[0]
# plt.ylim(0, 10**12)
def plotPerformance(self, values, window=1000):
plt.clf()
plt.plot(values[-window:])
plt.gcf().canvas.draw()
# Without the next line, the pyplot plot won't actually show up.
plt.pause(0.001)
def playAudio(self):
"""
指定されているwaveを再生
同時に波形をplot
"""
chunk = 22050 # 音源が0.5秒毎に切り替わっていたため.
data = self.wf.readframes(chunk)
#plt.ion()
#data_list = []
predictedInt = None
plt.figure(figsize=(15, 5))
while data != '':
dat = numpy.fromstring(data, dtype = "uint32")
#print(dat.shape, dat)
# plot
data_list = dat.tolist()
self.plotPerformance(data_list, window=500)
# plt.plot(dat)
# plt.show(block = False)
# plt.draw()
# 音ならす.
self.inStream.write(data)
# sampling値 -> SDR
actualInt, actual = self.encoder(data_list)
# actualInt, predictedInt 比較
if not predictedInt == None:
compare = self.vis.compareArray(actualInt, predictedInt)
print("." . join(compare) )
anomaly = self.vis.calcAnomaly(actualInt, predictedInt)
print(self.vis.hashtagAnomaly(anomaly) )
# TP predict
predictedInt = self.tp_learn_and_predict(actual)
# 次のデータ
data = self.wf.readframes(chunk)
self.inStream.close()
p.terminate()
def tp_learn_and_predict(self, data):
self.tp.compute(data, enableLearn = True, computeInfOutput = True)
predictedInt = self.tp.getPredictedState().max(axis=1)
return predictedInt
def encoder(self, data):
# sampling 値 -> 周波数成分
ys = self.fft(data, self.highpass, self.lowpass)
# 1. 強い周波数成分の上位numInputのindexを取得する.
# 2. 数字のレンジをnumColsに合わせる.
# 3. uniqにする. (いるの?)
fs = numpy.sort(ys.argsort()[-self.numInput:])
rfs = fs.astype(numpy.float32) / (self.lowpass - self.highpass) * self.numCols
ufs = numpy.unique(rfs)
# encode
actualInt = self.e.encode(ufs)
actual = actualInt.astype(numpy.float32)
return actualInt, actual
def fft(self, audio, highpass, lowpass):
left, right = numpy.split(numpy.abs(numpy.fft.fft(audio)), 2)
output = left[highpass:lowpass]
return output
def formatRow(self, x):
s = ''
for c in range(len(x)):
if c > 0 and c % 10 == 0:
s += ' '
s += str(x[c])
s += ' '
return s
def getAudioString(self):
if self.wf == None:
print(self.buffersToRecord)
for i in range(self.buffersToRecord):
try:
audioString = self.inStream.read(self.buffersize)
except IOError:
print("Overflow error from 'audiostring = inStream.read(buffersize)'. Try decreasing buffersize.")
quit()
self.audio[i*self.buffersize:(i+1)*self.buffersize] = numpy.fromstring(audioString, dtype = "uint32")
else:
for i in range(self.buffersToRecord):
audioString = self.wf.readframes(self.buffersize)
self.audio[i*self.buffersize:(i+1)*self.buffersize] = numpy.fromstring(audioString, dtype = "uint32")
def plotWave(self):
self.getAudioString()
print(self.audio)
plt.plot(audiostream.audio[0:1000])
plt.show()
def __init__(self):
"""
Instantiate temporal pooler, encoder, audio sampler, filter, & freq plot
"""
self.vis = Visualizations()
"""
The number of columns in the input and therefore the TP
2**9 = 512
Trial and error pulled that out
numCols should be tested during benchmarking
"""
self.numCols = 2 ** 9
sparsity = 0.10
self.numInput = int(self.numCols * sparsity)
"""
Create a bit map encoder
From the encoder's __init__ method:
1st arg: the total bits in input
2nd arg: the number of bits used to encode each input bit
"""
self.e = BitmapArrayEncoder(self.numCols, 1)
"""
Sampling details
rate: The sampling rate in Hz of my soundcard
buffersize: The size of the array to which we will save audio segments (2^12 = 4096 is very good)
secToRecord: The length of each sampling
buffersToRecord: how many multiples of buffers are we recording?
"""
rate = 44100
secToRecord = 0.1
self.buffersize = 2 ** 12
self.buffersToRecord = int(rate * secToRecord / self.buffersize)
if not self.buffersToRecord:
self.buffersToRecord = 1
"""
Filters in Hertz
highHertz: lower limit of the bandpass filter, in Hertz
lowHertz: upper limit of the bandpass filter, in Hertz
max lowHertz = (buffersize / 2 - 1) * rate / buffersize
"""
highHertz = 500
lowHertz = 10000
"""
Convert filters from Hertz to bins
highpass: convert the highHertz into a bin for the FFT
lowpass: convert the lowHertz into a bin for the FFt
NOTES:
highpass is at least the 1st bin since most mics only pick up >=20Hz
lowpass is no higher than buffersize/2 - 1 (highest array index)
passband needs to be wider than size of numInput - not checking for that
"""
self.highpass = max(int(highHertz * self.buffersize / rate), 1)
self.lowpass = min(int(lowHertz * self.buffersize / rate), self.buffersize / 2 - 1)
"""
The call to create the temporal pooler region
"""
self.tp = TP(
numberOfCols=self.numCols,
cellsPerColumn=4,
initialPerm=0.5,
connectedPerm=0.5,
minThreshold=10,
newSynapseCount=10,
permanenceInc=0.1,
permanenceDec=0.07,
activationThreshold=8,
globalDecay=0.02,
burnIn=2,
checkSynapseConsistency=False,
pamLength=100,
)
"""
Creating the audio stream from our mic
"""
p = pyaudio.PyAudio()
self.inStream = p.open(
format=pyaudio.paInt32, channels=1, rate=rate, input=True, frames_per_buffer=self.buffersize
)
"""
Setting up the array that will handle the timeseries of audio data from our input
"""
self.audio = numpy.empty((self.buffersToRecord * self.buffersize), dtype="uint32")
"""
Print out the inputs
"""
print "Number of columns:\t" + str(self.numCols)
print "Max size of input:\t" + str(self.numInput)
print "Sampling rate (Hz):\t" + str(rate)
print "Passband filter (Hz):\t" + str(highHertz) + " - " + str(lowHertz)
print "Passband filter (bin):\t" + str(self.highpass) + " - " + str(self.lowpass)
print "Bin difference:\t\t" + str(self.lowpass - self.highpass)
print "Buffersize:\t\t" + str(self.buffersize)
"""
Setup the plot
Use the bandpass filter frequency range as the x-axis
Rescale the y-axis
"""
plt.ion()
bin = range(self.highpass, self.lowpass)
xs = numpy.arange(len(bin)) * rate / self.buffersize + highHertz
self.freqPlot = plt.plot(xs, xs)[0]
plt.ylim(0, 10 ** 12)
while True:
self.processAudio()
class AudioStream:
def __init__(self):
"""
Instantiate temporal pooler, encoder, audio sampler, filter, & freq plot
"""
self.vis = Visualizations()
"""
The number of columns in the input and therefore the TP
2**9 = 512
Trial and error pulled that out
numCols should be tested during benchmarking
"""
self.numCols = 2 ** 9
sparsity = 0.10
self.numInput = int(self.numCols * sparsity)
"""
Create a bit map encoder
From the encoder's __init__ method:
1st arg: the total bits in input
2nd arg: the number of bits used to encode each input bit
"""
self.e = BitmapArrayEncoder(self.numCols, 1)
"""
Sampling details
rate: The sampling rate in Hz of my soundcard
buffersize: The size of the array to which we will save audio segments (2^12 = 4096 is very good)
secToRecord: The length of each sampling
buffersToRecord: how many multiples of buffers are we recording?
"""
rate = 44100
secToRecord = 0.1
self.buffersize = 2 ** 12
self.buffersToRecord = int(rate * secToRecord / self.buffersize)
if not self.buffersToRecord:
self.buffersToRecord = 1
"""
Filters in Hertz
highHertz: lower limit of the bandpass filter, in Hertz
lowHertz: upper limit of the bandpass filter, in Hertz
max lowHertz = (buffersize / 2 - 1) * rate / buffersize
"""
highHertz = 500
lowHertz = 10000
"""
Convert filters from Hertz to bins
highpass: convert the highHertz into a bin for the FFT
lowpass: convert the lowHertz into a bin for the FFt
NOTES:
highpass is at least the 1st bin since most mics only pick up >=20Hz
lowpass is no higher than buffersize/2 - 1 (highest array index)
passband needs to be wider than size of numInput - not checking for that
"""
self.highpass = max(int(highHertz * self.buffersize / rate), 1)
self.lowpass = min(int(lowHertz * self.buffersize / rate), self.buffersize / 2 - 1)
"""
The call to create the temporal pooler region
"""
self.tp = TP(
numberOfCols=self.numCols,
cellsPerColumn=4,
initialPerm=0.5,
connectedPerm=0.5,
minThreshold=10,
newSynapseCount=10,
permanenceInc=0.1,
permanenceDec=0.07,
activationThreshold=8,
globalDecay=0.02,
burnIn=2,
checkSynapseConsistency=False,
pamLength=100,
)
"""
Creating the audio stream from our mic
"""
p = pyaudio.PyAudio()
self.inStream = p.open(
format=pyaudio.paInt32, channels=1, rate=rate, input=True, frames_per_buffer=self.buffersize
)
"""
Setting up the array that will handle the timeseries of audio data from our input
"""
self.audio = numpy.empty((self.buffersToRecord * self.buffersize), dtype="uint32")
"""
Print out the inputs
"""
print "Number of columns:\t" + str(self.numCols)
print "Max size of input:\t" + str(self.numInput)
print "Sampling rate (Hz):\t" + str(rate)
print "Passband filter (Hz):\t" + str(highHertz) + " - " + str(lowHertz)
print "Passband filter (bin):\t" + str(self.highpass) + " - " + str(self.lowpass)
print "Bin difference:\t\t" + str(self.lowpass - self.highpass)
print "Buffersize:\t\t" + str(self.buffersize)
"""
Setup the plot
Use the bandpass filter frequency range as the x-axis
Rescale the y-axis
"""
plt.ion()
bin = range(self.highpass, self.lowpass)
xs = numpy.arange(len(bin)) * rate / self.buffersize + highHertz
self.freqPlot = plt.plot(xs, xs)[0]
plt.ylim(0, 10 ** 12)
while True:
self.processAudio()
def processAudio(self):
"""
Sample audio, encode, send it to the TP
Pulls the audio from the mic
Conditions that audio as an SDR
Computes a prediction via the TP
Update the visualizations
"""
"""
Cycle through the multiples of the buffers we're sampling
Sample audio to store for each frame in buffersize
Mic voltage-level timeseries is saved as 32-bit binary
Convert that 32-bit binary into integers, and save to array for the FFT
"""
for i in range(self.buffersToRecord):
try:
audioString = self.inStream.read(self.buffersize)
except IOError:
print "Overflow error from 'audiostring = inStream.read(buffersize)'. Try decreasing buffersize."
quit()
self.audio[i * self.buffersize : (i + 1) * self.buffersize] = numpy.fromstring(audioString, dtype="uint32")
"""
Get int array of strength for each bin of frequencies via fast fourier transform
Get the indices of the strongest frequencies (the top 'numInput')
Scale the indices so that the frequencies fit to within numCols
Pick out the unique indices (we've reduced the mapping, so we likely have multiples)
Encode those indices into an SDR via the BitmapArrayEncoder
Cast the SDR as a float for the TP
"""
ys = self.fft(self.audio, self.highpass, self.lowpass)
fs = numpy.sort(ys.argsort()[-self.numInput :])
rfs = fs.astype(numpy.float32) / (self.lowpass - self.highpass) * self.numCols
ufs = numpy.unique(rfs)
actualInt = self.e.encode(ufs)
actual = actualInt.astype(numpy.float32)
"""
Pass the SDR to the TP
Collect the prediction SDR from the TP
Pass the prediction & actual SDRS to the anomaly calculator & array comparer
Update the frequency plot
"""
self.tp.compute(actual, enableLearn=True, computeInfOutput=True)
predictedInt = self.tp.getPredictedState().max(axis=1)
compare = self.vis.compareArray(actualInt, predictedInt)
anomaly = self.vis.calcAnomaly(actualInt, predictedInt)
print ".".join(compare)
print self.vis.hashtagAnomaly(anomaly)
self.freqPlot.set_ydata(ys)
plt.show(block=False)
plt.draw()
def fft(self, audio, highpass, lowpass):
"""
Fast fourier transform conditioning
Output:
'output' contains the strength of each frequency in the audio signal
frequencies are marked by its position in 'output':
frequency = index * rate / buffesize
output.size = buffersize/2
Method:
Use numpy's FFT (numpy.fft.fft)
Find the magnitude of the complex numbers returned (abs value)
Split the FFT array in half, because we have mirror frequencies
(they're the complex conjugates)
Use just the first half to apply the bandpass filter
Great info here: http://stackoverflow.com/questions/4364823/how-to-get-frequency-from-fft-result
"""
left, right = numpy.split(numpy.abs(numpy.fft.fft(audio)), 2)
output = left[highpass:lowpass]
return output
class AudioStream:
def __init__(self):
"""
Instantiate temporal pooler, encoder, audio sampler, filter, & freq plot
"""
self.vis = Visualizations()
"""
The number of columns in the input and therefore the TP
2**9 = 512
Trial and error pulled that out
numCols should be tested during benchmarking
"""
self.numCols = 2**9
sparsity = 0.10
self.numInput = int(self.numCols * sparsity)
"""
Create a bit map encoder
From the encoder's __init__ method:
1st arg: the total bits in input
2nd arg: the number of bits used to encode each input bit
"""
self.e = BitmapArrayEncoder(self.numCols, 1)
"""
Sampling details
rate: The sampling rate in Hz of my soundcard
buffersize: The size of the array to which we will save audio segments (2^12 = 4096 is very good)
secToRecord: The length of each sampling
buffersToRecord: how many multiples of buffers are we recording?
"""
rate = 44100
secToRecord = .1
self.buffersize = 2**12
self.buffersToRecord = int(rate * secToRecord / self.buffersize)
if not self.buffersToRecord:
self.buffersToRecord = 1
"""
Filters in Hertz
highHertz: lower limit of the bandpass filter, in Hertz
lowHertz: upper limit of the bandpass filter, in Hertz
max lowHertz = (buffersize / 2 - 1) * rate / buffersize
"""
highHertz = 500
lowHertz = 10000
"""
Convert filters from Hertz to bins
highpass: convert the highHertz into a bin for the FFT
lowpass: convert the lowHertz into a bin for the FFt
NOTES:
highpass is at least the 1st bin since most mics only pick up >=20Hz
lowpass is no higher than buffersize/2 - 1 (highest array index)
passband needs to be wider than size of numInput - not checking for that
"""
self.highpass = max(int(highHertz * self.buffersize / rate), 1)
self.lowpass = min(int(lowHertz * self.buffersize / rate),
self.buffersize / 2 - 1)
"""
The call to create the temporal pooler region
"""
self.tp = TP(numberOfCols=self.numCols,
cellsPerColumn=4,
initialPerm=0.5,
connectedPerm=0.5,
minThreshold=10,
newSynapseCount=10,
permanenceInc=0.1,
permanenceDec=0.07,
activationThreshold=8,
globalDecay=0.02,
burnIn=2,
checkSynapseConsistency=False,
pamLength=100)
"""
Creating the audio stream from our mic
"""
p = pyaudio.PyAudio()
self.inStream = p.open(format=pyaudio.paInt32,
channels=1,
rate=rate,
input=True,
frames_per_buffer=self.buffersize)
"""
Setting up the array that will handle the timeseries of audio data from our input
"""
self.audio = numpy.empty((self.buffersToRecord * self.buffersize),
dtype="uint32")
"""
Print out the inputs
"""
print "Number of columns:\t" + str(self.numCols)
print "Max size of input:\t" + str(self.numInput)
print "Sampling rate (Hz):\t" + str(rate)
print "Passband filter (Hz):\t" + str(highHertz) + " - " + str(
lowHertz)
print "Passband filter (bin):\t" + str(self.highpass) + " - " + str(
self.lowpass)
print "Bin difference:\t\t" + str(self.lowpass - self.highpass)
print "Buffersize:\t\t" + str(self.buffersize)
"""
Setup the plot
Use the bandpass filter frequency range as the x-axis
Rescale the y-axis
"""
plt.ion()
bin = range(self.highpass, self.lowpass)
xs = numpy.arange(len(bin)) * rate / self.buffersize + highHertz
self.freqPlot = plt.plot(xs, xs)[0]
plt.ylim(0, 10**12)
while True:
self.processAudio()
def processAudio(self):
"""
Sample audio, encode, send it to the TP
Pulls the audio from the mic
Conditions that audio as an SDR
Computes a prediction via the TP
Update the visualizations
"""
"""
Cycle through the multiples of the buffers we're sampling
Sample audio to store for each frame in buffersize
Mic voltage-level timeseries is saved as 32-bit binary
Convert that 32-bit binary into integers, and save to array for the FFT
"""
for i in range(self.buffersToRecord):
try:
audioString = self.inStream.read(self.buffersize)
except IOError:
print "Overflow error from 'audiostring = inStream.read(buffersize)'. Try decreasing buffersize."
quit()
self.audio[i * self.buffersize:(i + 1) *
self.buffersize] = numpy.fromstring(audioString,
dtype="uint32")
"""
Get int array of strength for each bin of frequencies via fast fourier transform
Get the indices of the strongest frequencies (the top 'numInput')
Scale the indices so that the frequencies fit to within numCols
Pick out the unique indices (we've reduced the mapping, so we likely have multiples)
Encode those indices into an SDR via the BitmapArrayEncoder
Cast the SDR as a float for the TP
"""
ys = self.fft(self.audio, self.highpass, self.lowpass)
fs = numpy.sort(ys.argsort()[-self.numInput:])
rfs = fs.astype(
numpy.float32) / (self.lowpass - self.highpass) * self.numCols
ufs = numpy.unique(rfs)
actualInt = self.e.encode(ufs)
actual = actualInt.astype(numpy.float32)
"""
Pass the SDR to the TP
Collect the prediction SDR from the TP
Pass the prediction & actual SDRS to the anomaly calculator & array comparer
Update the frequency plot
"""
self.tp.compute(actual, enableLearn=True, computeInfOutput=True)
predictedInt = self.tp.getPredictedState().max(axis=1)
compare = self.vis.compareArray(actualInt, predictedInt)
anomaly = self.vis.calcAnomaly(actualInt, predictedInt)
print ".".join(compare)
print self.vis.hashtagAnomaly(anomaly)
self.freqPlot.set_ydata(ys)
plt.show(block=False)
plt.draw()
def fft(self, audio, highpass, lowpass):
"""
Fast fourier transform conditioning
Output:
'output' contains the strength of each frequency in the audio signal
frequencies are marked by its position in 'output':
frequency = index * rate / buffesize
output.size = buffersize/2
Method:
Use numpy's FFT (numpy.fft.fft)
Find the magnitude of the complex numbers returned (abs value)
Split the FFT array in half, because we have mirror frequencies
(they're the complex conjugates)
Use just the first half to apply the bandpass filter
Great info here: http://stackoverflow.com/questions/4364823/how-to-get-frequency-from-fft-result
"""
left, right = numpy.split(numpy.abs(numpy.fft.fft(audio)), 2)
output = left[highpass:lowpass]
return output
def __init__(self):
"""
Instantiate temporal pooler, encoder, audio sampler, filter, & freq plot
"""
self.vis = Visualizations()
"""
The number of columns in the input and therefore the TP
2**9 = 512
Trial and error pulled that out
numCols should be tested during benchmarking
"""
self.numCols = 2**9
sparsity = 0.10
self.numInput = int(self.numCols * sparsity)
"""
Create a bit map encoder
From the encoder's __init__ method:
1st arg: the total bits in input
2nd arg: the number of bits used to encode each input bit
"""
self.e = BitmapArrayEncoder(self.numCols, 1)
"""
Sampling details
rate: The sampling rate in Hz of my soundcard
buffersize: The size of the array to which we will save audio segments (2^12 = 4096 is very good)
secToRecord: The length of each sampling
buffersToRecord: how many multiples of buffers are we recording?
"""
rate = 44100
secToRecord = .1
self.buffersize = 2**12
self.buffersToRecord = int(rate * secToRecord / self.buffersize)
if not self.buffersToRecord:
self.buffersToRecord = 1
"""
Filters in Hertz
highHertz: lower limit of the bandpass filter, in Hertz
lowHertz: upper limit of the bandpass filter, in Hertz
max lowHertz = (buffersize / 2 - 1) * rate / buffersize
"""
highHertz = 500
lowHertz = 10000
"""
Convert filters from Hertz to bins
highpass: convert the highHertz into a bin for the FFT
lowpass: convert the lowHertz into a bin for the FFt
NOTES:
highpass is at least the 1st bin since most mics only pick up >=20Hz
lowpass is no higher than buffersize/2 - 1 (highest array index)
passband needs to be wider than size of numInput - not checking for that
"""
self.highpass = max(int(highHertz * self.buffersize / rate), 1)
self.lowpass = min(int(lowHertz * self.buffersize / rate),
self.buffersize / 2 - 1)
"""
The call to create the temporal pooler region
"""
self.tp = TP(numberOfCols=self.numCols,
cellsPerColumn=4,
initialPerm=0.5,
connectedPerm=0.5,
minThreshold=10,
newSynapseCount=10,
permanenceInc=0.1,
permanenceDec=0.07,
activationThreshold=8,
globalDecay=0.02,
burnIn=2,
checkSynapseConsistency=False,
pamLength=100)
"""
Creating the audio stream from our mic
"""
p = pyaudio.PyAudio()
self.inStream = p.open(format=pyaudio.paInt32,
channels=1,
rate=rate,
input=True,
frames_per_buffer=self.buffersize)
"""
Setting up the array that will handle the timeseries of audio data from our input
"""
self.audio = numpy.empty((self.buffersToRecord * self.buffersize),
dtype="uint32")
"""
Print out the inputs
"""
print "Number of columns:\t" + str(self.numCols)
print "Max size of input:\t" + str(self.numInput)
print "Sampling rate (Hz):\t" + str(rate)
print "Passband filter (Hz):\t" + str(highHertz) + " - " + str(
lowHertz)
print "Passband filter (bin):\t" + str(self.highpass) + " - " + str(
self.lowpass)
print "Bin difference:\t\t" + str(self.lowpass - self.highpass)
print "Buffersize:\t\t" + str(self.buffersize)
"""
Setup the plot
Use the bandpass filter frequency range as the x-axis
Rescale the y-axis
"""
plt.ion()
bin = range(self.highpass, self.lowpass)
xs = numpy.arange(len(bin)) * rate / self.buffersize + highHertz
self.freqPlot = plt.plot(xs, xs)[0]
plt.ylim(0, 10**12)
while True:
self.processAudio()
