Source Code for Module lib.fv_pdur

  1  #!/usr/bin/env python 
  2   
  3  """Duration estimator for speech. 
  4   
  5  It takes a local spectrum, 
  6  bins it onto the Bark scale, 
  7  converts to perceptual loudness (via **E). 
  8  Then, it computes a measure of how far you can go 
  9  from each point before the spectrum changes too much. 
 10  """ 
 11   
 12  import numpy 
 13  from gmisclib import cache as CC 
 14  from gmisclib import erb_scale 
 15   
 16  from gpk_voicing import cached_ps as PSC 
 17  from gpk_voicing import percep_spec as PS 
 18  from gpk_voicing import fv_misc as FVM 
 19  SillyWidthException = FVM.SillyWidthException 
 20  NSV = 0.75 
 21   
 22 -def _irx(a): 
 23          return max(1, int(round(a))) 
 24   
 25 -def feature_vec_guts(data, dt, Dt, do_irx=True, 
 26                  LF=1.0, Nsv=NSV, cache_info=None 
 27                  ): 
 28          FORMANT_LOW = erb_scale.f_to_erb(200.0) 
 29          FORMANT_HIGH = erb_scale.f_to_erb(4000.0) 
 30          assert Dt > 0.0 and float(Dt)>0.0 
 31          bmin = erb_scale.f_to_erb(100.0) 
 32          bmax = erb_scale.f_to_erb(6000.0) 
 33          # all_ectrs, all_ps, t0 = PS.perceptual_spec(data, dt, Dt, ... 
 34          if cache_info is not None: 
 35                  assert isinstance(cache_info, CC.cache_info) 
 36                  all_ectrs, all_ps, t0 = PSC.perceptual_spec(data, dt, Dt, 
 37                                                          bmin=bmin, bmax=bmax, db=FVM.DB, 
 38                                                          do_mod=0, 
 39                                                          do_dissonance=False, 
 40                                                          PlompBouman=False, 
 41                                                          cache_info=cache_info.copy() 
 42                                                          ) 
 43          else: 
 44                  all_ectrs, all_ps, t0 = PS.block_percep_spec(data, dt, Dt, 
 45                                                          bmin=bmin, bmax=bmax, db=FVM.DB, 
 46                                                          do_mod=0, 
 47                                                          do_dissonance=False, 
 48                                                          PlompBouman=False 
 49                                                          ) 
 50   
 51          band_indices = [i for (i,ec) in enumerate(all_ectrs) if ec['type']=='band'] 
 52          neural = all_ps.take(band_indices, axis=0) 
 53          ectrs = [ec for ec in all_ectrs if ec['type']=='band'] 
 54          nband_indices = [i for (i,ec) in enumerate(all_ectrs) if ec['type']!='band'] 
 55          nneural = all_ps.take(nband_indices, axis=0) 
 56          nectrs = [ec for ec in all_ectrs if ec['type']!='band'] 
 57   
 58          assert nneural.shape[1]==neural.shape[1] 
 59          assert neural.shape[1]==all_ps.shape[1] 
 60          assert neural.shape[0]+nneural.shape[0] == all_ps.shape[0] 
 61          assert len(data.shape) == 1 
 62          assert abs(all_ps.shape[1]*Dt-data.shape[0]*dt) < 0.1*data.shape[0]*dt 
 63   
 64          neural_now = numpy.average(neural, axis=0) 
 65          assert neural_now.shape[0] == neural.shape[1] 
 66          neural_avg = numpy.square(neural_now).sum()/numpy.sum(neural_now) 
 67          numpy.divide(neural, neural_avg, neural) 
 68          numpy.divide(neural_now, neural_avg, neural_now) 
 69   
 70          assert nneural.shape[0] < nneural.shape[1] 
 71          assert len(nectrs) == nneural.shape[0] 
 72          for (i,e) in enumerate(nectrs): 
 73                  assert e['type'] == 'band' 
 74   
 75          # print '# neural_avg=', neural_avg 
 76          w = 0.04 * LF / Dt 
 77          if do_irx: 
 78                  w = _irx(w) 
 79          o, descr = FVM.vowel(w, ectrs, neural, neural_now, Nsv, 
 80                                                  formant_low=FORMANT_LOW, 
 81                                                  formant_high=FORMANT_HIGH 
 82                                                  ) 
 83          assert len(descr)==len(o), "Descriptor mismatch" 
 84          return (o, descr, Dt, t0) 
 85   
 86   
 87 -def feature_vec(data, dt, DT, LF=1.0, Nsv=NSV, do_irx=True, cache_info=None): 
 88          o = None 
 89          ci = None 
 90          if cache_info is not None: 
 91                  assert isinstance(cache_info, CC.cache_info) 
 92                  ci = cache_info.addinfo(dt, DT, LF, Nsv, 'fv_pdur') 
 93                  try: 
 94                          o = ci.load() 
 95                  except ci.Errors: 
 96                          pass 
 97          if o is None: 
 98                  o = feature_vec_guts(data, dt, DT, LF=LF, Nsv=Nsv, 
 99                                          cache_info=cache_info 
100                                          ) 
101                  if ci is not None: 
102                          ci.bg_dump(o) 
103          return o 
104