annotate trunk/src/Scripts/Strobes_test.py @ 316:66a23c0545b6

-Added MFCCs back to the feature generation script

#!/usr/bin/env python
# encoding: utf-8
#
# AIM-C: A C++ implementation of the Auditory Image Model
# http://www.acousticscale.org/AIMC
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.
"""
Profiles_test.py

Created by Thomas Walters on 2010-02-22.
Copyright 2010 Thomas Walters <[e-mail]>
Test the AIM-C model from filterbank to SSI profiles
"""

import aimc
from scipy.io import wavfile
from scipy import io
import scipy
import pylab
import numpy
from itertools import izip, chain, repeat

def grouper(n, iterable, padvalue=None):
    "grouper(3, 'abcdefg', 'x') --> ('a','b','c'), ('d','e','f'), ('g','x','x')"
    return izip(*[chain(iterable, repeat(padvalue, n-1))]*n)
    
def BankToArray(out_bank):
  channel_count = out_bank.channel_count()
  out_buffer_length = out_bank.buffer_length()
  out = scipy.zeros((channel_count,out_buffer_length))
  for ch in range(0, channel_count):
    for i in range(0, out_buffer_length):  
      out[ch, i] = out_bank.sample(ch, i)
  return out

def StrobesToList(bank):
  channel_count = bank.channel_count()
  out = scipy.zeros((channel_count,), dtype=numpy.object)
  for ch in range(0, channel_count):
    s = []
    for i in range(0, bank.strobe_count(ch)):
      s.append(bank.strobe(ch, i))
    out[ch] = s
  return out

def main():
  wave_path = "/Users/Tom/Documents/Work/PhD/HTK-AIM/Sounds/"
  
  file_name = "ii/ii172.5p112.5s100.0t+000itd"
  
  wave_suffix = ".wav"
  
  frame_period_ms = 10;
    
  wave_filename = wave_path + file_name + wave_suffix
  
  (sample_rate, input_wave) = wavfile.read(wave_filename)
  wave_length = input_wave.size
  buffer_length = int(frame_period_ms * sample_rate / 1000)
 
  
  input_sig = aimc.SignalBank()
  input_sig.Initialize(1, buffer_length, sample_rate)
  parameters = aimc.Parameters()
  parameters.SetInt("input.buffersize", 480)

  mod_gt = aimc.ModuleGammatone(parameters)
  mod_hl = aimc.ModuleHCL(parameters)
  mod_strobes = aimc.ModuleLocalMax(parameters) 

  mod_gt.AddTarget(mod_hl)
  mod_hl.AddTarget(mod_strobes)

  mod_gt.Initialize(input_sig)
  
  correct_count = 0;
  incorrect_count  = 0;
  
  scaled_wave = []
  for sample in input_wave:
    scaled_wave.append(float(sample / float(pow(2,15) - 1)))
  i = 0
  
  wave_chunks = grouper(buffer_length, scaled_wave, 0)

  out_nap = []
  out_strobes = []

  for chunk in wave_chunks:
    i = 0
    for sample in chunk:
      input_sig.set_sample(0, i, float(sample))
      i += 1
    mod_gt.Process(input_sig) 
    out_nap.append(BankToArray(mod_hl.GetOutputBank()))
    out_strobes.append(StrobesToList(mod_strobes.GetOutputBank()))

  outmat = dict(nap=out_nap, strobes=out_strobes)
  io.savemat("src/Scripts/strobes_out.mat", outmat, oned_as='column')

  pass


if __name__ == '__main__':
  main()