def time_axis(self): sig = get_sig(self.args) fs = unroll_args(self.args, ['fs']) length = len(sig) t_end_sec = length / fs time = np.linspace(0, t_end_sec, length) return time
def energy_envelope(self): sig = get_sig(self.args) nfft = unroll_args(self.args, ['nfft']) sig = np.abs(sig) hann_window = _cached_get_window('hanning', nfft) envelope = np.convolve(sig, hann_window, 'same') return envelope
def spectral_flatness(self): psd = get_psd(self.args) nfft, noverlap = unroll_args(self.args, ['nfft', 'noverlap']) hopsize = nfft - noverlap return rosaft.spectral_flatness(y=None, S=psd, n_fft=nfft, hop_length=hopsize)
def total_energy(self): fs, nfft = unroll_args(self.args, ['fs', 'nfft']) psd = get_psd(self.args) # This is a little bit unclear. Eq (6.1) of Raven is the calculation below, but then it says it is in decibels, # which this is not! energy = np.sum(psd) * (fs / nfft) return energy
def mean_frequency(self): fs, nfft = unroll_args(self.args, ['fs', 'nfft']) s = self.mtspect() freq_range = nfft // 2 + 1 idx = np.arange(freq_range) tmp = s * idx.reshape((freq_range, 1)) x = np.sum(tmp, axis=0) / np.sum(s, axis=0) * fs / nfft return x
def zero_crossing_rate(self): sig = get_sig(self.args) nfft, noverlap = unroll_args(self.args, ['nfft', 'noverlap']) hopsize = nfft - noverlap zcr = rosaft.zero_crossing_rate(y=sig, frame_length=nfft, hop_length=hopsize, center=False) return zcr
def spectral_rolloff(self): psd = get_psd(self.args) fs, nfft, noverlap = unroll_args(self.args, ['fs', 'nfft', 'noverlap']) hopsize = nfft - noverlap return rosaft.spectral_rolloff(y=None, sr=fs, S=psd, n_fft=nfft, hop_length=hopsize)
def mfc(self): psd = get_psd(self.args) ** 2 fs, nfft, ncep, fmin, fmax = unroll_args(self.args, ['fs', 'nfft', ('ncep', 20), ('fmin', 0.0), ('fmax', None)]) if fmax is None: fmax = fs // 2 # Build a Mel filter mel_basis = _cached_get_mel_filter(sr=fs, n_fft=nfft, n_mels=ncep * 2, fmin=fmin, fmax=fmax) melspect = np.dot(mel_basis, psd) return power_to_db(melspect)
def lp_coefficients(self): sig = get_sig(self.args) nfft, fs, noverlap, win_length, order = unroll_args( self.args, ['nfft', 'fs', 'noverlap', 'win_length', 'order']) hann_window = _cached_get_window('hanning', nfft) window = unroll_args(self.args, [('window', hann_window)]) siglen = len(sig) nsegs, segs = split_segments(siglen, win_length, noverlap, incltail=False) lp_coeffs = np.zeros((order, nsegs), dtype=np.float32) for i in range(nsegs): seg_beg, seg_end = segs[i] frame = sig[seg_beg:seg_end] lp_coeffs[:, i] = lp_coefficients_frame(frame * window, order) return lp_coeffs
def lpc_spectrum(self): sig = get_sig(self.args) nfft, fs, noverlap, win_length, order = unroll_args( self.args, ['nfft', 'fs', 'noverlap', 'win_length', 'order']) hann_window = _cached_get_window('hanning', nfft) window = unroll_args(self.args, [('window', hann_window)]) siglen = len(sig) nsegs, segs = split_segments(siglen, win_length, noverlap, incltail=False) lpcs = np.zeros((nfft, nsegs), dtype=np.complex64) for i in range(nsegs): seg_beg, seg_end = segs[i] frame = sig[seg_beg:seg_end] lpcs[:, i] = lpc_spectrum_frame(frame * window, order, nfft) return np.log10(abs(lpcs))
def spectral_contrast(self): psd = get_psd(self.args) fs, nfft, noverlap = unroll_args(self.args, ['fs', 'nfft', 'noverlap']) hopsize = nfft - noverlap if fs < 12800: n_bands = 6 fmin = int(fs / 2.0**(n_bands)) else: fmin = 200 return rosaft.spectral_contrast(y=None, sr=fs, S=psd, n_fft=nfft, hop_length=hopsize, fmin=fmin)
def duration(self): start, end = unroll_args(self.args, ['start', 'end']) retval = np.ndarray((1, 1), dtype=np.float32) retval[0] = end - start return retval
def _harmonic_and_pitch(args): """ Computes harmonic ratio and pitch """ sig = get_sig(args) fs, noverlap, win_length = unroll_args(args, ['fs', 'noverlap', 'win_length']) siglen = len(sig) nsegs, segs = split_segments(siglen, win_length, noverlap, incltail=False) HRs = [] F0s = [] for i in range(nsegs): seg_beg, seg_end = segs[i] frame = sig[seg_beg:seg_end] M = int(np.round(0.016 * fs) - 1) R = np.correlate(frame, frame, mode='full') g = R[len(frame) - 1] R = R[len(frame):-1] # estimate m0 (as the first zero crossing of R) [ a, ] = np.nonzero(np.diff(np.sign(R))) if len(a) == 0: m0 = len(R) - 1 else: m0 = a[0] if M > len(R): M = len(R) - 1 Gamma = np.zeros(M, dtype=np.float64) CSum = np.cumsum(frame**2) Gamma[m0:M] = R[m0:M] / (np.sqrt((g * CSum[M:m0:-1])) + eps) ZCR = frame_zcr(Gamma) if ZCR > 0.15: HR = 0.0 f0 = 0.0 else: if len(Gamma) == 0: HR = 1.0 blag = 0.0 Gamma = np.zeros(M, dtype=np.float64) else: HR = np.max(Gamma) blag = np.argmax(Gamma) # Get fundamental frequency: f0 = fs / (blag + eps) if f0 > 5000: f0 = 0.0 if HR < 0.1: f0 = 0.0 HRs.append(HR) F0s.append(f0) return np.array(HRs), np.array(F0s)
def chroma_cens(self): sig = get_sig(self.args) fs, nfft, noverlap = unroll_args(self.args, ['fs', 'nfft', 'noverlap']) hopsize = nfft - noverlap return rosaft.chroma_cens(y=sig, sr=fs, hop_length=hopsize)
def chroma_stft(self): psd = get_psd(self.args) fs, nfft, noverlap = unroll_args(self.args, ['fs', 'nfft', 'noverlap']) hopsize = nfft - noverlap return rosaft.chroma_stft(y=None, sr=fs, S=psd, n_fft=nfft, hop_length=hopsize)
def mfcc(self): ncep = unroll_args(self.args, [('ncep', 20)]) S = self.mfc() return np.dot(filters.dct(ncep, S.shape[0]), S)