def main(inputFile='../../sounds/bendir.wav', window='hamming', M=2001, N=2048, t=-80, minSineDur=0.02, maxnSines=150, freqDevOffset=10, freqDevSlope=0.001): """ inputFile: input sound file (monophonic with sampling rate of 44100) window: analysis window type (rectangular, hanning, hamming, blackman, blackmanharris) M: analysis window size N: fft size (power of two, bigger or equal than M) t: magnitude threshold of spectral peaks minSineDur: minimum duration of sinusoidal tracks maxnSines: maximum number of parallel sinusoids freqDevOffset: frequency deviation allowed in the sinusoids from frame to frame at frequency 0 freqDevSlope: slope of the frequency deviation, higher frequencies have bigger deviation """ # size of fft used in synthesis Ns = 512 # hop size (has to be 1/4 of Ns) H = 128 # read input sound (fs, x) = UF.wavread(inputFile) # compute analysis window w = get_window(window, M) # perform sinusoidal plus residual analysis tfreq, tmag, tphase, xr = SPR.sprModelAnal(x, fs, w, N, H, t, minSineDur, maxnSines, freqDevOffset, freqDevSlope) # compute spectrogram of residual mXr, pXr = STFT.stftAnal(xr, fs, w, N, H) # sum sinusoids and residual y, ys = SPR.sprModelSynth(tfreq, tmag, tphase, xr, Ns, H, fs) # output sound file (monophonic with sampling rate of 44100) outputFileSines = 'output_sounds/' + os.path.basename( inputFile)[:-4] + '_sprModel_sines.wav' outputFileResidual = 'output_sounds/' + os.path.basename( inputFile)[:-4] + '_sprModel_residual.wav' outputFile = 'output_sounds/' + os.path.basename( inputFile)[:-4] + '_sprModel.wav' # write sounds files for sinusoidal, residual, and the sum UF.wavwrite(ys, fs, outputFileSines) UF.wavwrite(xr, fs, outputFileResidual) UF.wavwrite(y, fs, outputFile) return x, fs, mXr, tfreq, y
def main(inputFile='../../sounds/bendir.wav', window='hamming', M=2001, N=2048, t=-80, minSineDur=0.02, maxnSines=150, freqDevOffset=10, freqDevSlope=0.001): """ inputFile: input sound file (monophonic with sampling rate of 44100) window: analysis window type (rectangular, hanning, hamming, blackman, blackmanharris) M: analysis window size N: fft size (power of two, bigger or equal than M) t: magnitude threshold of spectral peaks minSineDur: minimum duration of sinusoidal tracks maxnSines: maximum number of parallel sinusoids freqDevOffset: frequency deviation allowed in the sinusoids from frame to frame at frequency 0 freqDevSlope: slope of the frequency deviation, higher frequencies have bigger deviation """ # size of fft used in synthesis Ns = 512 # hop size (has to be 1/4 of Ns) H = 128 # read input sound (fs, x) = UF.wavread(inputFile) # compute analysis window w = get_window(window, M) # perform sinusoidal plus residual analysis tfreq, tmag, tphase, xr = SPR.sprModelAnal(x, fs, w, N, H, t, minSineDur, maxnSines, freqDevOffset, freqDevSlope) # compute spectrogram of residual mXr, pXr = STFT.stftAnal(xr, fs, w, N, H) # sum sinusoids and residual y, ys = SPR.sprModelSynth(tfreq, tmag, tphase, xr, Ns, H, fs) # output sound file (monophonic with sampling rate of 44100) outputFileSines = 'output_sounds/' + os.path.basename(inputFile)[:-4] + '_sprModel_sines.wav' outputFileResidual = 'output_sounds/' + os.path.basename(inputFile)[:-4] + '_sprModel_residual.wav' outputFile = 'output_sounds/' + os.path.basename(inputFile)[:-4] + '_sprModel.wav' # write sounds files for sinusoidal, residual, and the sum UF.wavwrite(ys, fs, outputFileSines) UF.wavwrite(xr, fs, outputFileResidual) UF.wavwrite(y, fs, outputFile) return x, fs, mXr, tfreq, y
def main( path_to_original_dataset='/homedtic/vshenoykadandale/datasets/good-sounds/instruments' ): """ path_to_original_dataset: path to the original dataset whose residuals need to be separated. """ print("Checkpoint 1") path_to_residual_dataset = os.path.join( os.path.dirname(path_to_original_dataset), 'residuals') if not os.path.exists(path_to_residual_dataset): os.umask( 0 ) #To mask the permission restrictions on new files/directories being created os.makedirs(path_to_residual_dataset, 0o755) # 0o777 gives us full permissions for the folder print("Checkpoint 2") instruments = sorted(os.listdir(path_to_original_dataset)) for instrument in instruments: instrument_path = os.path.join(path_to_original_dataset, instrument) instrument_residual_path = os.path.join(path_to_residual_dataset, instrument) print("Checkpoint 3") if not os.path.exists(instrument_residual_path): os.umask( 0 ) #To mask the permission restrictions on new files/directories being created os.makedirs( instrument_residual_path, 0o755) # 0o777 gives us full permissions for the folder files = os.listdir(instrument_path) print("Processing [INSTRUMENT] " + instrument + " folder which contains " + str(len(files)) + " files") for filename in files: file_path = os.path.join(instrument_path, filename) file_residual_path = os.path.join(instrument_residual_path, filename[:-4] + '_residual.wav') wav = wavio.read(file_path) x = wav.data fs = wav.rate sampwidth = wav.sampwidth w = get_window("hamming", 2001) N = 2048 H = 128 minSineDur = 0.02 maxnSines = 150 freqDevOffset = 10 freqDevSlope = 0.001 t = -80 Ns = 512 # perform sinusoidal plus residual analysis tfreq, tmag, tphase, xr = SPR.sprModelAnal(x, fs, w, N, H, t, minSineDur, maxnSines, freqDevOffset, freqDevSlope) # compute spectrogram of residual #mXr, pXr = STFT.stftAnal(xr, w, N, H) # sum sinusoids and residual #y, ys = SPR.sprModelSynth(tfreq, tmag, tphase, xr, Ns, H, fs) #wavio.write(outputFileSines, ys, fs, sampwidth) wavio.write(file_residual_path, xr, fs, sampwidth=sampwidth) #wavio.write(outputFile, y, fs, sampwidth) print("Successfully extracted residuals from all the audio files!")
def main(inputFile='../../sounds/bendir.wav', window='hamming', M=2001, N=2048, t=-80, minSineDur=0.02, maxnSines=150, freqDevOffset=10, freqDevSlope=0.001): """ inputFile: input sound file (monophonic with sampling rate of 44100) window: analysis window type (rectangular, hanning, hamming, blackman, blackmanharris) M: analysis window size N: fft size (power of two, bigger or equal than M) t: magnitude threshold of spectral peaks minSineDur: minimum duration of sinusoidal tracks maxnSines: maximum number of parallel sinusoids freqDevOffset: frequency deviation allowed in the sinusoids from frame to frame at frequency 0 freqDevSlope: slope of the frequency deviation, higher frequencies have bigger deviation """ # size of fft used in synthesis Ns = 512 # hop size (has to be 1/4 of Ns) H = 128 # read input sound (fs, x) = UF.wavread(inputFile) # compute analysis window w = get_window(window, M) # perform sinusoidal plus residual analysis tfreq, tmag, tphase, xr = SPR.sprModelAnal(x, fs, w, N, H, t, minSineDur, maxnSines, freqDevOffset, freqDevSlope) # compute spectrogram of residual mXr, pXr = STFT.stftAnal(xr, w, N, H) # sum sinusoids and residual y, ys = SPR.sprModelSynth(tfreq, tmag, tphase, xr, Ns, H, fs) # output sound file (monophonic with sampling rate of 44100) outputFileSines = 'output_sounds/' + os.path.basename(inputFile)[:-4] + '_sprModel_sines.wav' outputFileResidual = 'output_sounds/' + os.path.basename(inputFile)[:-4] + '_sprModel_residual.wav' outputFile = 'output_sounds/' + os.path.basename(inputFile)[:-4] + '_sprModel.wav' # write sounds files for sinusoidal, residual, and the sum UF.wavwrite(ys, fs, outputFileSines) UF.wavwrite(xr, fs, outputFileResidual) UF.wavwrite(y, fs, outputFile) # create figure to show plots plt.figure(figsize=(12, 9)) # frequency range to plot maxplotfreq = 5000.0 # plot the input sound plt.subplot(3,1,1) plt.plot(np.arange(x.size)/float(fs), x) plt.axis([0, x.size/float(fs), min(x), max(x)]) plt.ylabel('amplitude') plt.xlabel('time (sec)') plt.title('input sound: x') # plot the magnitude spectrogram of residual plt.subplot(3,1,2) maxplotbin = int(N*maxplotfreq/fs) numFrames = int(mXr[:,0].size) frmTime = H*np.arange(numFrames)/float(fs) binFreq = np.arange(maxplotbin+1)*float(fs)/N plt.pcolormesh(frmTime, binFreq, np.transpose(mXr[:,:maxplotbin+1])) plt.autoscale(tight=True) # plot the sinusoidal frequencies on top of the residual spectrogram if (tfreq.shape[1] > 0): tracks = tfreq*np.less(tfreq, maxplotfreq) tracks[tracks<=0] = np.nan plt.plot(frmTime, tracks, color='k') plt.title('sinusoidal tracks + residual spectrogram') plt.autoscale(tight=True) # plot the output sound plt.subplot(3,1,3) plt.plot(np.arange(y.size)/float(fs), y) plt.axis([0, y.size/float(fs), min(y), max(y)]) plt.ylabel('amplitude') plt.xlabel('time (sec)') plt.title('output sound: y') plt.tight_layout() plt.ion() plt.show()
def extractHarmSpec(inputFile='../../sounds/bendir.wav', window='hamming', M=2001, N=2048, t=-80, minSineDur=0.02, maxnSines=150, freqDevOffset=10, freqDevSlope=0.001): """ inputFile: input sound file (monophonic with sampling rate of 44100) window: analysis window type (rectangular, hanning, hamming, blackman, blackmanharris) M: analysis window size N: fft size (power of two, bigger or equal than M) t: magnitude threshold of spectral peaks minSineDur: minimum duration of sinusoidal tracks maxnSines: maximum number of parallel sinusoids freqDevOffset: frequency deviation allowed in the sinusoids from frame to frame at frequency 0 freqDevSlope: slope of the frequency deviation, higher frequencies have bigger deviation """ # size of fft used in synthesis Ns = 512 # hop size (has to be 1/4 of Ns) H = 128 # read input sound (fs, x) = UF.wavread(inputFile) # compute analysis window w = get_window(window, M) # perform sinusoidal plus residual analysis tfreq, tmag, tphase, xr = SPR.sprModelAnal(x, fs, w, N, H, t, minSineDur, maxnSines, freqDevOffset, freqDevSlope) # compute spectrogram of residual mXr, pXr = STFT.stftAnal(xr, fs, w, N, H) # sum sinusoids and residual y, ys = SPR.sprModelSynth(tfreq, tmag, tphase, xr, Ns, H, fs) # output sound file (monophonic with sampling rate of 44100) outputFileSines = 'output_sounds/' + os.path.basename( inputFile)[:-4] + '_sprModel_sines.wav' outputFileResidual = 'output_sounds/' + os.path.basename( inputFile)[:-4] + '_sprModel_residual.wav' outputFile = 'output_sounds/' + os.path.basename( inputFile)[:-4] + '_sprModel.wav' # write sounds files for sinusoidal, residual, and the sum UF.wavwrite(ys, fs, outputFileSines) UF.wavwrite(xr, fs, outputFileResidual) UF.wavwrite(y, fs, outputFile) # create figure to show plots plt.figure(figsize=(12, 9)) # frequency range to plot maxplotfreq = 5000.0 # plot the input sound plt.subplot(3, 1, 1) plt.plot(np.arange(x.size) / float(fs), x) plt.axis([0, x.size / float(fs), min(x), max(x)]) plt.ylabel('amplitude') plt.xlabel('time (sec)') plt.title('input sound: x') # plot the magnitude spectrogram of residual plt.subplot(3, 1, 2) maxplotbin = int(N * maxplotfreq / fs) numFrames = int(mXr[:, 0].size) frmTime = H * np.arange(numFrames) / float(fs) binFreq = np.arange(maxplotbin + 1) * float(fs) / N plt.pcolormesh(frmTime, binFreq, np.transpose(mXr[:, :maxplotbin + 1])) plt.autoscale(tight=True) # plot the sinusoidal frequencies on top of the residual spectrogram if (tfreq.shape[1] > 0): tracks = tfreq * np.less(tfreq, maxplotfreq) tracks[tracks <= 0] = np.nan plt.plot(frmTime, tracks, color='k') plt.title('sinusoidal tracks + residual spectrogram') plt.autoscale(tight=True) # plot the output sound plt.subplot(3, 1, 3) plt.plot(np.arange(y.size) / float(fs), y) plt.axis([0, y.size / float(fs), min(y), max(y)]) plt.ylabel('amplitude') plt.xlabel('time (sec)') plt.title('output sound: y') plt.tight_layout() plt.show()