Python samplerate.resample函数代码示例

  def play(self):
    if not self.sound:
      self.sound   = pygame.mixer.Sound(self.file)
      self.freq = self.info.rate
    if resampleOk:
        (freq,format,channels) = pygame.mixer.get_init()
        if freq != self.freq:
          print "reload sound ",self.file
          self.freq = self.info.rate
          self.sound   = pygame.mixer.Sound(self.file)
        if self.freq != freq:
            snd_array = pygame.sndarray.array(self.sound)
            samples = len(snd_array)/2
            samples = int(samples*freq*1.0/(self.info.rate))
            print "start resampling ",self.file," from ",self.info.rate," to ",freq," len ",len(snd_array)/2," visée ",samples
    #        if samples != len(snd_array):
    #          snd_array = np.resize(snd_array,(samples,2))
            snd_array = resample(snd_array, freq*1.0/self.info.rate, "sinc_fastest").astype(snd_array.dtype)
            # datal = signal.resample(snd_array[0::2],samples).astype(snd_array.dtype)
            # datar = signal.resample(snd_array[1::2],samples).astype(snd_array.dtype)
            # snd_array = np.resize(snd_array,(len(datal)*2,2))
            # snd_array[0::2] = datal
            # snd_array[1::2] = datar
            # print "end resampling ",snd_array
            self.sound = pygame.sndarray.make_sound(snd_array)
            self.freq = freq

    if self.volume:
      self.sound.set_volume(self.volume)
    self.channel = self.sound.play()
    self.playTime = time.time()
    if self.event:
        self.channel.set_endevent(self.event)

def strfpak_resample(sound,slice_rate,resample_type):
    
    '''
    Resample a sound object using scikits.samplerate.resample.
    Sound is upsampled to nearest multiple of slice_rate;
    if sound.samplerate == slice_rate, no resampling is done.
    Sound is also converted to float.
    Currently, error is less than 10dB max, mostly very good.
    '''
    
    from scikits.samplerate import resample
    from copy import deepcopy
    
    # Calculate the resampling frequency for STRFPAK 5.3:
    # round up to the nearest multiple of 'slice_rate'
    input_freq = floor(sound.samplerate)
    output_freq = ceil(input_freq/slice_rate)*slice_rate
    
    # Copy so that we don't alter original object
    sound2 = deepcopy(sound)
    
    # Scale factor -- MATLAB makes .wav data be -1:1, scipy does integer
    sound2.data = sound2.data/float(2**15)
    
    # Resample if necessary
    if output_freq > input_freq:
        sound2.data = resample(sound2.data,output_freq/input_freq,
                               resample_type)
        sound2.samplerate = output_freq
    
        # Pad because matlab resampling works differently
        sound2.data = sound2._zeropad(0,2)
    
    return sound2

def convert_wav(File, ofile):
    import scikits.audiolab as audiolab
    from scikits.samplerate import resample
    # lastest scikits.audiolab include sound record lib, based on python-alsaaudio
    # if you want make the down sample rate using scipy.signal
    #import scipy.signal

    #using audiolab to read wav file
    Signal, fs = audiolab.wavread(File)[:2]
    #changing the original sample rate to 16000fs fast mode
    Signal = resample(Signal, fr/float(fs), 'sinc_best')
     
    #changing sample rate from audio file using scipy this is a bit slow
    #Signal=scipy.signal.resample(Signal,int(round(len(Getsignal)*fr)/float(fs)),window=None)
     
    # file Format type
    fmt = audiolab.Format('flac', 'pcm16')
    nchannels   = 1
     
    # convert into the file .flac
    ofile =  audiolab.Sndfile(FileNameTmp, 'w', fmt, nchannels, fr)
     
    #writing in the file
    ofile.write_frames(Signal)
    #
    return ofile

def wav_convert(data, SR, tar_freq):

    # If the input signal is stereo, make it mono.
    if ndim(data) == 2:

        # Mix stereo signal into a mono signal
        buff01 = 0.49 * (data[:, 0] + data[:, 1])
        wave_ts = array(buff01)

    else:
        wave_ts = array(data[:])

    wave_ts = array(wave_ts)

    # Set a sampling rate
    up_SR = 44100

    # Compute a ratio to feed into resample function
    ratio = float(float(tar_freq)/float(up_SR))

    # Resample the file.
    wave_ts = resample(wave_ts, ratio , 'linear')

    # Transpose the data list.
    wave_ts = transpose(wave_ts)

    # Return wave_ts signal
    return wave_ts

    def record(self, signals, Fs):
        '''
        This simulates the recording of the signals by the microphones.
        In particular, if the microphones and the room simulation
        do not use the same sampling frequency, down/up-sampling
        is done here.

        Arguments:
        ----------

        signals: An ndarray with as many lines as there are microphones.
        Fs: the sampling frequency of the signals.
        '''

        if signals.shape[0] != self.M:
            raise NameError('The signals array should have as many lines as there are microphones.')

        if signals.ndim != 2:
            raise NameError('The signals should be a 2D array.')

        if Fs != self.Fs:
            from scikits.samplerate import resample
            Fs_ratio = self.Fs/float(Fs)
            newL = int(Fs_ratio*signals.shape[1])-1
            self.signals = np.zeros((self.M, newL))
            # scikits.samplerate resample function considers columns as channels (hence the transpose)
            for m in range(self.M):
                self.signals[m] = resample(signals[m], Fs_ratio, 'sinc_best')
        else:
            self.signals = signals

def resample(y, orig_sr, target_sr, res_type='sinc_fastest'):
    """Resample a signal from orig_sr to target_sr

    Arguments:
      y           -- (ndarray)    audio time series 
      orig_sr     -- (int)        original sample rate of y
      target_sr   -- (int)        target sample rate
      res_type    -- (str)        resample type (see below)
    
    Returns y_hat:
      y_hat       -- (ndarray)    y resampled from orig_sr to target_sr

    Notes:
        if scikits.samplerate is installed, resample will use res_type
        otherwise, it will fall back on scip.signal.resample
    """

    if orig_sr == target_sr:
        return y

    if _HAS_SAMPLERATE:
        y_hat = samplerate.resample(y, 
                                            float(target_sr) / orig_sr, 
                                            res_type)
    else:
        n_samples = len(y) * target_sr / orig_sr
        y_hat = scipy.signal.resample(y, n_samples, axis=-1)

    return y_hat

def analyze(sig, samplerate=8000, resample_to=8000):
    e_min_scale = 0.3
    e_min_distance = 1
    e_a_scale = 0.5
    e_W_ms = 2000
    min_len = 30
    if samplerate != resample_to:
        print("resampling")
        sig = srate.resample(sig, resample_to/samplerate, 'sinc_best')

    frames,frame_size = ad.frames(sig, samplerate, 64)
    #ac_peaks = [ad.ac_peaks(frame) for frame in frames]
    #energy = ad.energies(frames, ...)
    #energy = log_energy
    print("getting normalized spectra")
    normalized_spectrum = ad.normalized_spectrum(frames, samplerate)
    print("spectral entropy")
    spectral_entropy = np.fromiter(ad.entropy(frame) for frame in normalized_spectrum)
    entopy_t = np.percentile(spectral_entropy, 80)
    se_segments = ad.segments_to_seconds(ad.entropy_segment_indexes(spectral_entropy, entropy_t))
    print("energy based computations")
    energy, smooth, en_a, en_t, en_lmin = ad.energy_thresholds(sig, noise_dist=e_min_distance, a_scale=e_a_scale, min_scale=e_min_scale, W_ms=e_W_ms)
    energy_segments = ad.get_voice_segments(smooth, en_t, ad.get_segment_indexes(smooth, en_t, min_len=10))
    #energy_t = ad.thresholds(frames)
    #entropy_t = ad.entropy_t(frames)
    #energy_indexes = ad.get_segment_indexes(x, t, min_len=30)
    #entropy_indexes = ad.get_entropy_indexes(x, t, min_len=30)
    #combination_indexes = ad.get_combined_indexes(x, t, min_len=30)
    return spectral_entropy, se_t, se_segments, energy, en_t, energy_segments

	def calculate_attributes(self):
		source = self.source
		freq = self.frequency
		sampling_rate = float(source.sampling_rate)
		fft_sampling_rate = sampling_rate/float(source.fft_step_size)
		window_length = float(source.fft_window_size)/sampling_rate
		# FIXME real time should be passed in as an extra field
		self.start = window_length
		if self.first_frame > 0:
			self.start += (self.first_frame - 1)/fft_sampling_rate
		self.length = window_length
		if len(freq) > 1:
#			if 'length' not in self.__dict__:
#				print self.__dict__
#			print self.__dict__['length']
			self.length += (len(freq) - 1)/fft_sampling_rate
#		print self.length
		self.end = self.start + self.length
		for k in ('frequency','amplitude'):
			a = getattr(self,k)
			setattr(self, k+'_min', min(a))
			setattr(self, k+'_max', max(a))
			setattr(self, k+'_mean', sum(a)/len(a))
		freq_window = 2 # seconds
		freq_fft_size = 128
		resampled_freq = resample(freq, freq_window*freq_fft_size/fft_sampling_rate, 'sinc_fastest') # FIXME truncate array?
		self.freq_fft = abs(rfft(resampled_freq,n=freq_fft_size,overwrite_x=True))[1:]

    def generate_scale(self):
        """
        Given the initial note, middle C, create the rest of the musical scale by
        resampling.
    
        Returns: Dictionary of musical scale with the key being the name of the note
        and the value being the corresponding sound object.
    
        """    
        pygame.mixer.init()
    
        wav = util.get_app_path() + "res/piano-c.wav"
        sound = pygame.mixer.Sound(wav)
        
        pygame.mixer.set_num_channels(32)
        sndarray = pygame.sndarray.array(sound)

        ratio_dict = {'low_c': 1, 'c_sharp': .944, 'd': .891, 'd_sharp':.841, 'e':.794,
                  'f':.749, 'f_sharp': .707, 'g': .667, 'g_sharp': .63, 'a': .594,
                  'a_sharp': .561, 'b':.53, 'high_c':.5}
    
        # Generate the Sound objects from the dictionary.
        scale = {}
        for key,value in ratio_dict.iteritems():
            smp = resample(sndarray, value,"sinc_fastest").astype(sndarray.dtype)
            # Use the key, currently a string, as a variable
            scale[key] = pygame.sndarray.make_sound(smp)
            
        self.scale_dict=scale

def listen(stream, queue):
    try:
        while not exit:
            stream.start_stream()
            print('Listening...')
            for i in range(0,size):
                data = stream.read(frame)
                ar = numpy.fromstring(data, dtype=numpy.int16)
                data2 = resample(ar, (16000./48000.), 'linear')
                q.put(data2)
#                samps = numpy.fromstring(data, dtype=numpy.int16)
#                print (samps, q.qsize())
                rms = audioop.rms(data, 2)
                print rms
            stream.stop_stream()
            if exit:
                sys.exit()
            q.join()
    except IOError:
        print('ERROR!!!!')
        pass
    stream.stop_stream()
    stream.close()
    pyaud.terminate()
    print "----------------------------------------------------------------------------------------------------------------"

def wav_convert(data, SR, tar_freq):

    # If the input signal is stereo, make it mono.
    if ndim(data) == 2:
        buff01 = 0.49 * (data[:, 0] + data[:, 1])
        wave_ts = array(buff01)
    else:
        wave_ts = array(data[:])

    wave_ts = array(wave_ts)
    # print "Shape of wave_ts", shape(wave_ts)

    up_SR = 44100
    ratio = float(float(tar_freq)/float(up_SR))
    print tar_freq
    print float(float(tar_freq)/float(up_SR))
    wave_ts = resample(wave_ts, ratio , 'linear')

    # SR_div = int(floor(up_SR/tar_freq))
    # wave_ts = sig.decimate(wave_ts, SR_div)

    # Transpose the data list.
    wave_ts = transpose(wave_ts)
    print 'length wave_ts', shape(wave_ts)

    return wave_ts

def __stream_audio_realtime(filepath, rate=44100):
    total_chunks = 0
    format = pyaudio.paInt16
    channels = 1 if sys.platform == 'darwin' else 2
    record_cap = 10 # seconds
    p = pyaudio.PyAudio()
    stream = p.open(format=format, channels=channels, rate=rate, input=True, frames_per_buffer=ASR.chunk_size)
    print "o\t recording\t\t(Ctrl+C to stop)"
    try:
        desired_rate = float(desired_sample_rate) / rate # desired_sample_rate is an INT. convert to FLOAT for division.
        for i in range(0, rate/ASR.chunk_size*record_cap):
            data = stream.read(ASR.chunk_size)
            _raw_data = numpy.fromstring(data, dtype=numpy.int16)
            _resampled_data = resample(_raw_data, desired_rate, "sinc_best").astype(numpy.int16).tostring()
            total_chunks += len(_resampled_data)
            stdout.write("\r  bytes sent: \t%d" % total_chunks)
            stdout.flush()
            yield _resampled_data
        stdout.write("\n\n")
    except KeyboardInterrupt:
        pass
    finally:
        print "x\t done recording"
        stream.stop_stream()
        stream.close()
        p.terminate()   

def train_codebook(basedirectory,
                   spectral,
                   desired_fs,
                   clfs,
                   n_samples):
    """Train the codebooks.

    Arguments:
    :param basedirectory: root directory of the audio corpus
    :param spectral:
      Spectral feature extraction.
      Object should be picklable and implement the
      \c Spectral abc; i.e. provide a \c transform method.
    :param clfs:
      list of clusterers. valid clusterers have a \c fit method
      and a \c predict method. optionally, for soft vq, also implement
      a \c predict_proba method.
    :param n_samples:
      number of spectral frames to sample from the audio corpus.
    :returns:
      a list of Codebook objects, of same length as the output of spectral_func
    """
    wavs = list(rglob(basedirectory, '*.wav'))
    np.random.shuffle(wavs)

    inds = None
    idx = 0
    X = None
    for i, wav in enumerate(wavs):
        if i % 10 == 0 and i > 0:
            print 'samples: {3}/{4}; loading file: {0} ({1}/{2})'.format(
                wavs[i],
                i+1,
                len(wavs),
                X.shape[0],
                n_samples
            )
        sig, fs, _ = audiolab.wavread(wav)
        start, stop = trim_silence(sig, fs)
        specs = spectral.transform(samplerate.resample(sig[start:stop],
                                                       desired_fs/fs,
                                                       'sinc_best'))
        if inds is None:
            inds = [0] + list(np.cumsum([spec.shape[1] for spec in specs]))
        spec = np.hstack(specs)
        if idx + spec.shape[0] >= n_samples:
            spec = spec[:n_samples - idx, :]
        if X is None:
            X = spec
        else:
            X = np.vstack((X, spec))
        idx += spec.shape[0]
        if idx >= n_samples:
            break

    cdbs = [Codebook(clf) for clf in clfs]
    for i, cdb in enumerate(cdbs):
        cdb.train(X[:, inds[i]:inds[i+1]])
    return cdbs

 def resample(self, samplerate, resample_type="sinc_best"):
     """
     Returns a resampled version of the sound.
     """
     if not have_scikits_samplerate:
         raise ImportError("Need scikits.samplerate package for resampling")
     y = array(resample(self, float(samplerate / self.samplerate), resample_type), dtype=float64)
     return Sound(y, samplerate=samplerate)

def TestGBPDN2():    
    # ________________________________________
    print 'Test: generalized basis pursuit decomposition'

    fs = 8000.
    btmp,fstmp,fmt = audiolab.wavread('glockenspiel.wav')
    b = samplerate.resample(btmp, fs/fstmp,'sinc_best')
    L = len(b)

    A = GaborBlock(L,1024)
    B = GaborBlock(A.M,64)
    C = DictionaryUnion(A,B)
    b = np.hstack((b,np.zeros(C.M-L))) # pad to block boundary
    spow = 10*np.log10(b.conj().dot(b))
    
    # additive white noise
    snr = 15
    nvar = np.sum(np.abs(b)**2)/(10**(snr/10)) # 1e-2    
    n = np.sqrt(nvar)*np.random.randn(C.M)/np.sqrt(C.M)
    
    tonemap = np.reshape(range(A.N),(A.N/A.fftLen,A.fftLen)).transpose()
    transmap = np.reshape(range(B.N),(B.N/B.fftLen,B.fftLen)).transpose()
    
    f,fgrad = BP_factory()
    #f,fgrad = TT_factory(tonemap,transmap)
        
    xe = GBPDN_momentum(C,b+n,f,fgrad,maxerr=nvar,maxits=200,stoptol=1e-3,muinit=1e-1,momentum=0.9,smoothinit=1e-5,anneal=0.96)    
    ye = np.real(C.dot(xe))
    r = b-ye;
    rpow = 10*np.log10(r.conj().dot(r))
                       
    print 'SNR = %f' % (spow-rpow)

    ynoise = np.array(samplerate.resample(b+n,fstmp/fs,'sinc_best'),dtype='float64')
    ydenoise = np.array(samplerate.resample(ye,fstmp/fs,'sinc_best'),dtype='float64')
    
    yetone = np.real(A.dot(xe[:tonemap.size]))
    yetone = np.array(samplerate.resample(yetone,fstmp/fs,'sinc_best'),dtype='float64')

    yetrans = np.real(B.dot(xe[tonemap.size:]))
    yetrans = np.array(samplerate.resample(yetrans,fstmp/fs,'sinc_best'),dtype='float64')
    
                      
    print 'Error (should be <= %f): %f' % (nvar,np.sum((r)**2))
    print '----------------------------------------'