示例#1
0
文件: base.py 项目: fitz04/MyToy
def ssc(signal,samplerate=16000,winlen=0.025,winstep=0.01,
          nfilt=26,nfft=512,lowfreq=0,highfreq=None,preemph=0.97):
    """Compute Spectral Subband Centroid features from an audio signal.

    :param signal: the audio signal from which to compute features. Should be an N*1 array
    :param samplerate: the samplerate of the signal we are working with.
    :param winlen: the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)    
    :param winstep: the step between successive windows in seconds. Default is 0.01s (10 milliseconds)    
    :param nfilt: the number of filters in the filterbank, default 26.
    :param nfft: the FFT size. Default is 512.
    :param lowfreq: lowest band edge of mel filters. In Hz, default is 0.
    :param highfreq: highest band edge of mel filters. In Hz, default is samplerate/2
    :param preemph: apply preemphasis filter with preemph as coefficient. 0 is no filter. Default is 0.97. 
    :returns: A numpy array of size (NUMFRAMES by nfilt) containing features. Each row holds 1 feature vector. 
    """          
    highfreq= highfreq or samplerate/2
    signal = sigproc.preemphasis(signal,preemph)
    frames = sigproc.framesig(signal, winlen*samplerate, winstep*samplerate)
    pspec = sigproc.powspec(frames,nfft)
    pspec = numpy.where(pspec == 0,numpy.finfo(float).eps,pspec) # if things are all zeros we get problems
    
    fb = get_filterbanks(nfilt,nfft,samplerate,lowfreq,highfreq)
    feat = numpy.dot(pspec,fb.T) # compute the filterbank energies
    R = numpy.tile(numpy.linspace(1,samplerate/2,numpy.size(pspec,1)),(numpy.size(pspec,0),1))
    
    return numpy.dot(pspec*R,fb.T) / feat
示例#2
0
文件: base.py 项目: fitz04/MyToy
def fbank(signal,samplerate=16000,winlen=0.025,winstep=0.01,
          nfilt=26,nfft=512,lowfreq=0,highfreq=None,preemph=0.97):
    """Compute Mel-filterbank energy features from an audio signal.

    :param signal: the audio signal from which to compute features. Should be an N*1 array
    :param samplerate: the samplerate of the signal we are working with.
    :param winlen: the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)    
    :param winstep: the step between successive windows in seconds. Default is 0.01s (10 milliseconds)    
    :param nfilt: the number of filters in the filterbank, default 26.
    :param nfft: the FFT size. Default is 512.
    :param lowfreq: lowest band edge of mel filters. In Hz, default is 0.
    :param highfreq: highest band edge of mel filters. In Hz, default is samplerate/2
    :param preemph: apply preemphasis filter with preemph as coefficient. 0 is no filter. Default is 0.97. 
    :returns: 2 values. The first is a numpy array of size (NUMFRAMES by nfilt) containing features. Each row holds 1 feature vector. The
        second return value is the energy in each frame (total energy, unwindowed)
    """          
    highfreq= highfreq or samplerate/2
    signal = sigproc.preemphasis(signal,preemph)
    frames = sigproc.framesig(signal, winlen*samplerate, winstep*samplerate)
    pspec = sigproc.powspec(frames,nfft)
    energy = numpy.sum(pspec,1) # this stores the total energy in each frame
    energy = numpy.where(energy == 0,numpy.finfo(float).eps,energy) # if energy is zero, we get problems with log
        
    fb = get_filterbanks(nfilt,nfft,samplerate,lowfreq,highfreq)
    feat = numpy.dot(pspec,fb.T) # compute the filterbank energies
    feat = numpy.where(feat == 0,numpy.finfo(float).eps,feat) # if feat is zero, we get problems with log
    
    return feat,energy
示例#3
0
def fbank(signal,
          samplerate=16000,
          winlen=0.025,
          winstep=0.01,
          nfilt=26,
          nfft=512,
          lowfreq=0,
          highfreq=None,
          preemph=0.97):
    """Compute Mel-filterbank energy features from an audio signal.

    :param signal: the audio signal from which to compute features. Should be an N*1 array
    :param samplerate: the samplerate of the signal we are working with.
    :param winlen: the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)    
    :param winstep: the step between successive windows in seconds. Default is 0.01s (10 milliseconds)    
    :param nfilt: the number of filters in the filterbank, default 26.
    :param nfft: the FFT size. Default is 512.
    :param lowfreq: lowest band edge of mel filters. In Hz, default is 0.
    :param highfreq: highest band edge of mel filters. In Hz, default is samplerate/2
    :param preemph: apply preemphasis filter with preemph as coefficient. 0 is no filter. Default is 0.97. 
    :returns: 2 values. The first is a numpy array of size (NUMFRAMES by nfilt) containing features. Each row holds 1 feature vector. The
        second return value is the energy in each frame (total energy, unwindowed)
    """
    highfreq = highfreq or samplerate / 2
    signal = sigproc.preemphasis(signal, preemph)
    frames = sigproc.framesig(signal, winlen * samplerate,
                              winstep * samplerate)
    pspec = sigproc.powspec(frames, nfft)
    energy = numpy.sum(pspec, 1)  # this stores the total energy in each frame
    energy = numpy.where(energy == 0,
                         numpy.finfo(float).eps,
                         energy)  # if energy is zero, we get problems with log

    fb = get_filterbanks(nfilt, nfft, samplerate, lowfreq, highfreq)
    feat = numpy.dot(pspec, fb.T)  # compute the filterbank energies
    feat = numpy.where(feat == 0,
                       numpy.finfo(float).eps,
                       feat)  # if feat is zero, we get problems with log

    return feat, energy
示例#4
0
def ssc(signal,
        samplerate=16000,
        winlen=0.025,
        winstep=0.01,
        nfilt=26,
        nfft=512,
        lowfreq=0,
        highfreq=None,
        preemph=0.97):
    """Compute Spectral Subband Centroid features from an audio signal.

    :param signal: the audio signal from which to compute features. Should be an N*1 array
    :param samplerate: the samplerate of the signal we are working with.
    :param winlen: the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)    
    :param winstep: the step between successive windows in seconds. Default is 0.01s (10 milliseconds)    
    :param nfilt: the number of filters in the filterbank, default 26.
    :param nfft: the FFT size. Default is 512.
    :param lowfreq: lowest band edge of mel filters. In Hz, default is 0.
    :param highfreq: highest band edge of mel filters. In Hz, default is samplerate/2
    :param preemph: apply preemphasis filter with preemph as coefficient. 0 is no filter. Default is 0.97. 
    :returns: A numpy array of size (NUMFRAMES by nfilt) containing features. Each row holds 1 feature vector. 
    """
    highfreq = highfreq or samplerate / 2
    signal = sigproc.preemphasis(signal, preemph)
    frames = sigproc.framesig(signal, winlen * samplerate,
                              winstep * samplerate)
    pspec = sigproc.powspec(frames, nfft)
    pspec = numpy.where(pspec == 0,
                        numpy.finfo(float).eps,
                        pspec)  # if things are all zeros we get problems

    fb = get_filterbanks(nfilt, nfft, samplerate, lowfreq, highfreq)
    feat = numpy.dot(pspec, fb.T)  # compute the filterbank energies
    R = numpy.tile(numpy.linspace(1, samplerate / 2, numpy.size(pspec, 1)),
                   (numpy.size(pspec, 0), 1))

    return numpy.dot(pspec * R, fb.T) / feat