def output(partIdx):
"""Uses the student code to compute the output for test cases."""
outputString = ''
if partIdx == 0: # This is ScaledFFTdB
from assignment1 import scaled_fft_db
r,x = wavfile.read('data/a1_submissionInput.wav')
X = scaled_fft_db(x)
for val in X:
outputString += '%.5f ' % (val)
elif partIdx == 1: # This is PrototypeFilter
from assignment2 import prototype_filter
h = prototype_filter()
# test signal
s = np.loadtxt('data/a2_submissionInput.txt')
r = np.convolve(h, s)[4*512:5*512]/2
for val in r:
outputString += '%.5f ' % val
elif partIdx == 2: # This is SubbandFiltering
from assignment3 import subband_filtering
r,x = wavfile.read('data/a3_submissionInput.wav')
h = np.hanning(512)
X = subband_filtering(x, h)
for val in X:
outputString += '%.5f ' % (val)
elif partIdx == 3: # This is Quantization
from assignment4 import quantization
from parameters import EncoderParameters
params = EncoderParameters(44100, 2, 64)
val_in = np.loadtxt('data/a4_submissionInput.txt')
for r,row in enumerate(val_in):
val = row[0]
scf = row[1]
ba = int(row[2])
QCa = params.table.qca[ba-2]
QCb = params.table.qcb[ba-2]
val = quantization(val, scf, ba, QCa, QCb)
outputString += '%d ' % (val)
return outputString.strip()
def output(partIdx):
"""Uses the student code to compute the output for test cases."""
outputString = ''
if partIdx == 0: # This is ScaledFFTdB
from assignment1 import scaled_fft_db
r, x = wavfile.read('data/a1_submissionInput.wav')
X = scaled_fft_db(x)
for val in X:
outputString += '%.5f ' % (val)
elif partIdx == 1: # This is PrototypeFilter
from assignment2 import prototype_filter
h = prototype_filter()
# test signal
s = np.loadtxt('data/a2_submissionInput.txt')
r = np.convolve(h, s)[4 * 512:5 * 512] / 2
for val in r:
outputString += '%.5f ' % val
elif partIdx == 2: # This is SubbandFiltering
from assignment3 import subband_filtering
r, x = wavfile.read('data/a3_submissionInput.wav')
h = np.hanning(512)
X = subband_filtering(x, h)
for val in X:
outputString += '%.5f ' % (val)
elif partIdx == 3: # This is Quantization
from assignment4 import quantization
from parameters import EncoderParameters
params = EncoderParameters(44100, 2, 64)
val_in = np.loadtxt('data/a4_submissionInput.txt')
for r, row in enumerate(val_in):
val = row[0]
scf = row[1]
ba = int(row[2])
QCa = params.table.qca[ba - 2]
QCb = params.table.qcb[ba - 2]
val = quantization(val, scf, ba, QCa, QCb)
outputString += '%d ' % (val)
return outputString.strip()
def output(partIdx):
outputString = ""
if partIdx == "1": # This is ScaledFFTdB
from assignment1 import scaled_fft_db
r, x = wavfile.read("data/a1_submissionInput.wav")
X = scaled_fft_db(x)
for val in X:
outputString += "%.5f " % (val)
elif partIdx == "2": # This is PrototypeFilter
from assignment2 import prototype_filter
h = prototype_filter()
# test signal
s = np.loadtxt("data/a2_submissionInput.txt")
r = np.convolve(h, s)[4 * 512:5 * 512] / 2
for val in r:
outputString += "%.5f " % val
elif partIdx == "3": # This is SubbandFiltering
from assignment3 import subband_filtering
r, x = wavfile.read("data/a3_submissionInput.wav")
h = np.hanning(512)
X = subband_filtering(x, h)
for val in X:
outputString += "%.5f " % (val)
elif partIdx == "4": # This is Quantization
from assignment4 import quantization
from parameters import EncoderParameters
params = EncoderParameters(44100, 2, 64)
val_in = np.loadtxt("data/a4_submissionInput.txt")
for r, row in enumerate(val_in):
val = row[0]
scf = row[1]
ba = int(row[2])
QCa = params.table.qca[ba - 2]
QCb = params.table.qcb[ba - 2]
val = quantization(val, scf, ba, QCa, QCb)
outputString += "%d " % (val)
else:
print("Unknown assigment part number")
if len(outputString) > 0:
fileName = "res%s.txt" % partIdx
with open(fileName, "w") as f:
f.write(outputString.strip())
print("You can now submit the file " + fileName)
else:
print(
"there was an error with the computation. Please check your code")
def output(partIdx):
outputString = ''
if partIdx == '1': # This is ScaledFFTdB
from assignment1 import scaled_fft_db
r,x = wavfile.read('data/a1_submissionInput.wav')
X = scaled_fft_db(x)
for val in X:
outputString += '%.5f ' % (val)
elif partIdx == '2': # This is PrototypeFilter
from assignment2 import prototype_filter
h = prototype_filter()
# test signal
s = np.loadtxt('data/a2_submissionInput.txt')
r = np.convolve(h, s)[4*512:5*512]/2
for val in r:
outputString += '%.5f ' % val
elif partIdx == '3': # This is SubbandFiltering
from assignment3 import subband_filtering
r,x = wavfile.read('data/a3_submissionInput.wav')
h = np.hanning(512)
X = subband_filtering(x, h)
for val in X:
outputString += '%.5f ' % (val)
elif partIdx == '4': # This is Quantization
from assignment4 import quantization
from parameters import EncoderParameters
params = EncoderParameters(44100, 2, 64)
val_in = np.loadtxt('data/a4_submissionInput.txt')
for r,row in enumerate(val_in):
val = row[0]
scf = row[1]
ba = int(row[2])
QCa = params.table.qca[ba-2]
QCb = params.table.qcb[ba-2]
val = quantization(val, scf, ba, QCa, QCb)
outputString += '%d ' % (val)
else:
print "Unknown assigment part number"
if len(outputString) > 0:
fileName = "res%s.txt" % partIdx;
with open(fileName, "w") as f:
f.write(outputString.strip())
print "You can now submit the file " + fileName
else:
print "there was an error with the computation. Please check your code"
def main(inwavfile, outmp3file, bitrate):
"""Encoder main function."""
#inwavfile = "../samples/sinestereo.wav"
#outmp3file = "../samples/sinestereo.mp3"
#bitrate = 320
# Read WAVE file and set MPEG encoder parameters.
input_buffer = WavRead(inwavfile)
params = EncoderParameters(input_buffer.fs, input_buffer.nch, bitrate)
# Subband filter calculation from baseband prototype.
# Very detailed analysis of MP3 subband filtering available at
# http://cnx.org/content/m32148/latest/?collection=col11121/latest
# Read baseband filter samples
"""
ASSIGNMENT 2
"""
baseband_filter = assignment2.prototype_filter().astype('float32')
subband_samples = np.zeros((params.nch, N_SUBBANDS, FRAMES_PER_BLOCK),
dtype='float32')
# Main loop, executing until all samples have been processed.
while input_buffer.nprocessed_samples < input_buffer.nsamples:
# In each block 12 frames are processed, which equals 12x32=384 new samples per block.
for frm in range(FRAMES_PER_BLOCK):
samples_read = input_buffer.read_samples(SHIFT_SIZE)
# If all samples have been read, perform zero padding.
if samples_read < SHIFT_SIZE:
for ch in range(params.nch):
input_buffer.audio[ch].insert(
np.zeros(SHIFT_SIZE - samples_read))
# Filtering = dot product with reversed buffer.
"""
ASSIGNMENT 3 : Subband filtering
"""
for ch in range(params.nch):
subband_samples[ch, :, frm] = assignment3.subband_filtering(
input_buffer.audio[ch].reversed(), baseband_filter)
# Declaring arrays for keeping table indices of calculated scalefactors and bits allocated in subbands.
# Number of bits allocated in subband is either 0 or in range [2,15].
scfindices = np.zeros((params.nch, N_SUBBANDS), dtype='uint8')
subband_bit_allocation = np.zeros((params.nch, N_SUBBANDS),
dtype='uint8')
smr = np.zeros((params.nch, N_SUBBANDS), dtype='float32')
# Finding scale factors, psychoacoustic model and bit allocation calculation for subbands. Although
# scaling is done later, its result is necessary for the psychoacoustic model and calculation of
# sound pressure levels.
for ch in range(params.nch):
scfindices[ch, :] = get_scalefactors(subband_samples[ch, :, :],
params.table.scalefactor)
subband_bit_allocation[ch, :] = psycho.model1(
input_buffer.audio[ch].ordered(), params, scfindices)
"""
ASSIGNMENT 4 : Quantization
"""
subband_samples_quantized = np.zeros(subband_samples.shape,
dtype='uint32')
for ch in range(params.nch):
for sb in range(N_SUBBANDS):
QCa = params.table.qca[subband_bit_allocation[ch, sb] - 2]
QCb = params.table.qcb[subband_bit_allocation[ch, sb] - 2]
scf = params.table.scalefactor[scfindices[ch, sb]]
ba = subband_bit_allocation[ch, sb]
for ind in range(FRAMES_PER_BLOCK):
subband_samples_quantized[ch, sb,
ind] = assignment4.quantization(
subband_samples[ch, sb, ind],
scf, ba, QCa, QCb)
# Forming output bitsream and appending it to the output file.
bitstream_formatting(outmp3file, params, subband_bit_allocation,
scfindices, subband_samples_quantized)
def main(inwavfile, outmp3file, bitrate):
"""Encoder main function."""
#inwavfile = "../samples/sinestereo.wav"
#outmp3file = "../samples/sinestereo.mp3"
#bitrate = 320
# Read WAVE file and set MPEG encoder parameters.
input_buffer = WavRead(inwavfile)
params = EncoderParameters(input_buffer.fs, input_buffer.nch, bitrate)
# Subband filter calculation from baseband prototype.
# Very detailed analysis of MP3 subband filtering available at
# http://cnx.org/content/m32148/latest/?collection=col11121/latest
# Read baseband filter samples
"""
ASSIGNMENT 2
"""
baseband_filter = assignment2.prototype_filter().astype('float32')
subband_samples = np.zeros((params.nch, N_SUBBANDS, FRAMES_PER_BLOCK), dtype='float32')
# Main loop, executing until all samples have been processed.
while input_buffer.nprocessed_samples < input_buffer.nsamples:
# In each block 12 frames are processed, which equals 12x32=384 new samples per block.
for frm in range(FRAMES_PER_BLOCK):
samples_read = input_buffer.read_samples(SHIFT_SIZE)
# If all samples have been read, perform zero padding.
if samples_read < SHIFT_SIZE:
for ch in range(params.nch):
input_buffer.audio[ch].insert(np.zeros(SHIFT_SIZE - samples_read))
# Filtering = dot product with reversed buffer.
"""
ASSIGNMENT 3 : Subband filtering
"""
for ch in range(params.nch):
subband_samples[ch,:,frm] = assignment3.subband_filtering(input_buffer.audio[ch].reversed(), baseband_filter)
# Declaring arrays for keeping table indices of calculated scalefactors and bits allocated in subbands.
# Number of bits allocated in subband is either 0 or in range [2,15].
scfindices = np.zeros((params.nch, N_SUBBANDS), dtype='uint8')
subband_bit_allocation = np.zeros((params.nch, N_SUBBANDS), dtype='uint8')
smr = np.zeros((params.nch, N_SUBBANDS), dtype='float32')
# Finding scale factors, psychoacoustic model and bit allocation calculation for subbands. Although
# scaling is done later, its result is necessary for the psychoacoustic model and calculation of
# sound pressure levels.
for ch in range(params.nch):
scfindices[ch,:] = get_scalefactors(subband_samples[ch,:,:], params.table.scalefactor)
subband_bit_allocation[ch,:] = psycho.model1(input_buffer.audio[ch].ordered(), params,scfindices)
"""
ASSIGNMENT 4 : Quantization
"""
subband_samples_quantized = np.zeros(subband_samples.shape, dtype='uint32')
for ch in range(params.nch):
for sb in range(N_SUBBANDS):
QCa = params.table.qca[subband_bit_allocation[ch,sb]-2]
QCb = params.table.qcb[subband_bit_allocation[ch,sb]-2]
scf = params.table.scalefactor[scfindices[ch,sb]]
ba = subband_bit_allocation[ch,sb]
for ind in range(FRAMES_PER_BLOCK):
subband_samples_quantized[ch,sb,ind] = assignment4.quantization(subband_samples[ch,sb,ind], scf, ba, QCa, QCb)
# Forming output bitsream and appending it to the output file.
bitstream_formatting(outmp3file,
params,
subband_bit_allocation,
scfindices,
subband_samples_quantized)