def estimate_f0_B(filenames):
### ASSUME: all filenames are of the same instrument-string
wav_filename = filenames[0]
basename='-'.join(os.path.basename(wav_filename).split('-')[0:3])
if basename.startswith("test-440f"):
return 440.0, 0, 1, 1, 1, 1
### get initial f0 estimate
base_frequency_estimate = expected_frequencies.get_freq_from_filename(
wav_filename)
### get noise
initial_noise_floor, initial_noise_freqs, _, _, _ = calc_noise.get_noise(wav_filename)
noise_cutoff = stft.db2amplitude(
stft.amplitude2db(initial_noise_floor)+defs.B_MINIMUM_HARMONIC_SNR)
#### get FFT frames from audio files
sample_rate = None
freqs = None
estimate_B_buffers_list = []
for wav_i, wav_filename in enumerate(filenames):
#print wav_filename
#window_buffer, sample_rate = stft.get_long_buffer_from_file(wav_filename,
window_buffers, sample_rate = stft.get_buffers_from_file(wav_filename,
(defs.B_NUM_BUFFERS_ESTIMATE))
if freqs is None:
freqs = [ stft.bin2hertz(i, sample_rate)
for i in range(stft.WINDOWSIZE/2+1) ]
estimate_B_buffers_this_list = []
#fft_amplitude = stft.fft_amplitude(window_buffer, sample_rate)
#estimate_B_buffers_this_list.append(fft_amplitude)
for window_number in range(defs.B_NUM_BUFFERS_ESTIMATE):
window_buffer = window_buffers[window_number]
fft_amplitude = stft.stft_amplitude(window_buffer)
estimate_B_buffers_this_list.append(fft_amplitude)
estimate_B_buffers_list.extend(estimate_B_buffers_this_list)
estimate_B_buffers = numpy.array(estimate_B_buffers_list)
### radius of search area for peaks
# used with STFT only
bin_initial_estimate = stft.hertz2bin(base_frequency_estimate,
sample_rate)
#bin_initial_estimate = (base_frequency_estimate
# * fft_amplitude.shape[0] / (sample_rate/2)
# )
#print bin_initial_estimate
bin_spread_below = int(math.ceil(abs(
stft.hertz2bin(
(1.0-defs.B_PEAK_SPREAD_BELOW_HERTZ)*base_frequency_estimate,
sample_rate) - bin_initial_estimate)))
bin_spread_above = int(math.ceil(
stft.hertz2bin(
(1.0+defs.B_PEAK_SPREAD_ABOVE_HERTZ)*base_frequency_estimate,
sample_rate) - bin_initial_estimate))
#bin_spread_below = int(round(bin_initial_estimate *
# defs.B_PEAK_SPREAD_BELOW_HERTZ))
#bin_spread_above = int(round(bin_initial_estimate *
# defs.B_PEAK_SPREAD_BELOW_HERTZ))
#bin_spread_below_main = int(
# stft.hertz2bin(defs.STFT_PEAK_SPREAD_BELOW_HERTZ*base_frequency_estimate,
# sample_rate))
#bin_spread_above_main = int(
# stft.hertz2bin(defs.STFT_PEAK_SPREAD_ABOVE_HERTZ*base_frequency_estimate,
# sample_rate))
### actual estimate
bin_f0, B, rsquared, harmonics, limit = get_bin_f0_B(
bin_initial_estimate,
estimate_B_buffers, noise_cutoff,
#estimate_B_buffers, numpy.zeros(defs.LONG_WINDOWSIZE+1),
bin_spread_below, bin_spread_above, sample_rate)
highest_harmonic = 0
for h in harmonics:
if highest_harmonic < h.n:
highest_harmonic = h.n
limit = min(limit, highest_harmonic)
# HACK: remove limit
#limit = defs.TOTAL_HARMONICS
#print "limit to:", limit
#harmonics_enable = [True]*defs.TOTAL_HARMONICS
harmonics_enable = [True]*limit
bins_estimate = [ partials.mode_B2freq(bin_f0, i, B) for
i in range(1,len(harmonics_enable)+1) ]
bins_naive = [ i*bin_f0 for
i in range(1,len(harmonics_enable)+1) ]
if defs.B_PLOT:
pylab.figure()
pylab.plot(initial_noise_freqs,
stft.amplitude2db(initial_noise_floor), color='black')
#pylab.plot(initial_noise_freqs,
# stft.amplitude2db(initial_noise_floor)+defs.B_MINIMUM_HARMONIC_SNR,
# color='black')
pylab.xlabel("Frequency (seconds)")
pylab.ylabel("Power (/ dB)")
for i in range(estimate_B_buffers.shape[0]):
#color = matplotlib.cm.spring(float(wav_i)/len(filenames))
#color = matplotlib.cm.RdYlGn(
#color = matplotlib.cm.spring(
# float(i)/len(estimate_B_buffers_this_list))
pylab.plot(freqs,
stft.amplitude2db(estimate_B_buffers[i,:]),
#color=color,
color="orange",
alpha=0.5,
label=basename,
)
for est in bins_estimate:
low = stft.bin2hertz(est - bin_spread_below, sample_rate)
high = stft.bin2hertz(est + bin_spread_above, sample_rate)
if True:
pylab.axvspan(low, high, color='c', alpha=0.3)
else:
pylab.axvline(stft.bin2hertz(est, sample_rate),
color='cyan', alpha=0.3,
#linewidth=2.0
)
for naive in bins_naive:
freq = stft.bin2hertz(naive, sample_rate)
pylab.axvline(freq, color='grey', alpha=0.2,
#linewidth=2.0
)
for j, harm in enumerate(harmonics):
if harm.mag == 0:
continue
fn = stft.bin2hertz(harm.fft_bin, sample_rate)
mag = stft.amplitude2db(harm.mag)
#pylab.plot(fn, mag, 'o',
# color='green'
# )
pylab.xlabel("Frequency")
pylab.ylabel("Decibels")
if defs.B_DUMP_HARMS:
t_fns = []
t_mags = []
for j, harm in enumerate(harmonics):
if harm.mag == 0:
continue
fn = stft.bin2hertz(harm.fft_bin, sample_rate)
mag = stft.amplitude2db(harm.mag)
t_fns.append(fn)
t_mags.append(mag)
data = numpy.vstack((t_fns, t_mags)).transpose()
numpy.savetxt("B-harms.txt", data)
if defs.B_PLOT:
pylab.show()
f0 = stft.bin2hertz(bin_f0, sample_rate)
stiff_ideal_limit = stiff_ideal_conflict.find_limit(bin_f0, B,
bin_spread_below, bin_spread_above)
lim = min(stiff_ideal_limit, limit)
detected_freqs = StringFreqsB(f0, B, lim)
stats = StringFreqsB_stats()
stats.num_files = len(filenames)
stats.rsquared = rsquared
stats.highest_mode_detected = limit
stats.highest_mode_stiff_ideal = stiff_ideal_limit
stats.basename = basename
adjusted_B, delta_fn = adjust_B.adjust(basename, limit, f0, B)
if adjusted_B is not None:
stiff_ideal_lim_adjusted = stiff_ideal_conflict.find_limit(
bin_f0, adjusted_B,
bin_spread_below, bin_spread_above)
lim = min(stiff_ideal_lim_adjusted, limit)
adjusted_freqs = StringFreqsB(f0, adjusted_B, lim)
adjusted_freqs.delta_fn = delta_fn
stats.highest_mode_stiff_ideal_adjusted = stiff_ideal_lim_adjusted
stats.delta_fn = delta_fn
final = StringFreqsB(f0, adjusted_B,
min(stats.highest_mode_detected,
stats.highest_mode_stiff_ideal,
stiff_ideal_lim_adjusted))
else:
adjusted_freqs = None
final = StringFreqsB(f0, B,
min(stats.highest_mode_detected,
stats.highest_mode_stiff_ideal))
return detected_freqs, adjusted_freqs, stats, final
def write_plot(base_filename):
filenames = glob.glob(os.path.join(
base_filename, "spectrum-*.txt"))
basename = base_filename.split('/')[-2]
wav_filename = os.path.split(
os.path.dirname(base_filename)
)[-1]
base_freq = expected_frequencies.get_freq_from_filename(wav_filename)
filenames.sort()
Bs = numpy.loadtxt(os.path.join(base_filename, 'Bs.txt'))
SAMPLE_RATE, base_freq, B, limit, below, above = Bs
limit = int(limit)
num_harms = None
for i, filename in enumerate(filenames):
seconds = i*HOPSIZE / float(SAMPLE_RATE)
if seconds > MAX_SECONDS:
print "Reached time cutoff of %.1f" % MAX_SECONDS
return
print i, filename
fft = numpy.loadtxt(filename)
harms = numpy.loadtxt(filename.replace("spectrum-", "harms-"))
#noise = numpy.loadtxt(os.path.join(
# base_filename, "noise-floor.txt"))
outfilename = filename.replace("spectrum-","").replace(".txt", ".png")
freqs_estimate_int = [ i*base_freq for
i in range(1,limit+1)]
freqs_estimate_B = [ partials.mode_B2freq(base_freq, i, B) for
i in range(1,limit+1)]
# DEBUG for g string only
for j, freq in enumerate(freqs_estimate_int):
if j == 0:
pylab.axvline(freq, color="y", label="ideal freq.")
else:
pylab.axvline(freq, color="y")
for j, freq in enumerate(freqs_estimate_B):
low = stft.bin2hertz( stft.hertz2bin(freq, SAMPLE_RATE)
- below, SAMPLE_RATE)
high = stft.bin2hertz( stft.hertz2bin(freq,
SAMPLE_RATE) + above, SAMPLE_RATE)
if j == 0:
pylab.axvspan(low, high, color="c", alpha=0.3,
label="search range")
else:
pylab.axvspan(low, high, color="c", alpha=0.3)
pylab.plot(fft[:,0], fft[:,1])
pylab.plot(harms[:,0], harms[:,1], 'ro', label="peaks")
#pylab.semilogy(noise[:,0], noise[:,1], 'g-')
if num_harms is None:
num_harms = len(harms[:,0])
#pylab.xlim([0, (num_harms+3)*base_freq])
if max_freq > 0:
pylab.xlim([min_freq, max_freq])
pylab.ylim([AXIS_Y_BOTTOM, AXIS_Y_TOP])
pylab.xlabel("Frequency [Hz]")
pylab.ylabel("Amplitude [dB]")
pylab.title("Evolution of harmonics: %s\n%.3fs seconds" % (
basename, seconds))
#pylab.legend(bbox_to_anchor=(1.05, 1), loc=2)
pylab.legend()
pylab.savefig(outfilename)
pylab.close()
def write_plot(base_filename):
filenames = glob.glob(os.path.join(base_filename, "spectrum-*.txt"))
basename = base_filename.split('/')[-2]
wav_filename = os.path.split(os.path.dirname(base_filename))[-1]
base_freq = expected_frequencies.get_freq_from_filename(wav_filename)
filenames.sort()
Bs = numpy.loadtxt(os.path.join(base_filename, 'Bs.txt'))
SAMPLE_RATE, base_freq, B, limit, below, above = Bs
limit = int(limit)
num_harms = None
for i, filename in enumerate(filenames):
seconds = i * HOPSIZE / float(SAMPLE_RATE)
if seconds > MAX_SECONDS:
print "Reached time cutoff of %.1f" % MAX_SECONDS
return
print i, filename
fft = numpy.loadtxt(filename)
harms = numpy.loadtxt(filename.replace("spectrum-", "harms-"))
#noise = numpy.loadtxt(os.path.join(
# base_filename, "noise-floor.txt"))
outfilename = filename.replace("spectrum-", "").replace(".txt", ".png")
freqs_estimate_int = [i * base_freq for i in range(1, limit + 1)]
freqs_estimate_B = [
partials.mode_B2freq(base_freq, i, B) for i in range(1, limit + 1)
]
# DEBUG for g string only
for j, freq in enumerate(freqs_estimate_int):
if j == 0:
pylab.axvline(freq, color="y", label="ideal freq.")
else:
pylab.axvline(freq, color="y")
for j, freq in enumerate(freqs_estimate_B):
low = stft.bin2hertz(
stft.hertz2bin(freq, SAMPLE_RATE) - below, SAMPLE_RATE)
high = stft.bin2hertz(
stft.hertz2bin(freq, SAMPLE_RATE) + above, SAMPLE_RATE)
if j == 0:
pylab.axvspan(low,
high,
color="c",
alpha=0.3,
label="search range")
else:
pylab.axvspan(low, high, color="c", alpha=0.3)
pylab.plot(fft[:, 0], fft[:, 1])
pylab.plot(harms[:, 0], harms[:, 1], 'ro', label="peaks")
#pylab.semilogy(noise[:,0], noise[:,1], 'g-')
if num_harms is None:
num_harms = len(harms[:, 0])
#pylab.xlim([0, (num_harms+3)*base_freq])
if max_freq > 0:
pylab.xlim([min_freq, max_freq])
pylab.ylim([AXIS_Y_BOTTOM, AXIS_Y_TOP])
pylab.xlabel("Frequency [Hz]")
pylab.ylabel("Amplitude [dB]")
pylab.title("Evolution of harmonics: %s\n%.3fs seconds" %
(basename, seconds))
#pylab.legend(bbox_to_anchor=(1.05, 1), loc=2)
pylab.legend()
pylab.savefig(outfilename)
pylab.close()
def estimate_f0_B(filenames):
### ASSUME: all filenames are of the same instrument-string
wav_filename = filenames[0]
basename = '-'.join(os.path.basename(wav_filename).split('-')[0:3])
if basename.startswith("test-440f"):
return 440.0, 0, 1, 1, 1, 1
### get initial f0 estimate
base_frequency_estimate = expected_frequencies.get_freq_from_filename(
wav_filename)
### get noise
initial_noise_floor, initial_noise_freqs, _, _, _ = calc_noise.get_noise(
wav_filename)
noise_cutoff = stft.db2amplitude(
stft.amplitude2db(initial_noise_floor) + defs.B_MINIMUM_HARMONIC_SNR)
#### get FFT frames from audio files
sample_rate = None
freqs = None
estimate_B_buffers_list = []
for wav_i, wav_filename in enumerate(filenames):
#print wav_filename
#window_buffer, sample_rate = stft.get_long_buffer_from_file(wav_filename,
window_buffers, sample_rate = stft.get_buffers_from_file(
wav_filename, (defs.B_NUM_BUFFERS_ESTIMATE))
if freqs is None:
freqs = [
stft.bin2hertz(i, sample_rate)
for i in range(stft.WINDOWSIZE / 2 + 1)
]
estimate_B_buffers_this_list = []
#fft_amplitude = stft.fft_amplitude(window_buffer, sample_rate)
#estimate_B_buffers_this_list.append(fft_amplitude)
for window_number in range(defs.B_NUM_BUFFERS_ESTIMATE):
window_buffer = window_buffers[window_number]
fft_amplitude = stft.stft_amplitude(window_buffer)
estimate_B_buffers_this_list.append(fft_amplitude)
estimate_B_buffers_list.extend(estimate_B_buffers_this_list)
estimate_B_buffers = numpy.array(estimate_B_buffers_list)
### radius of search area for peaks
# used with STFT only
bin_initial_estimate = stft.hertz2bin(base_frequency_estimate, sample_rate)
#bin_initial_estimate = (base_frequency_estimate
# * fft_amplitude.shape[0] / (sample_rate/2)
# )
#print bin_initial_estimate
bin_spread_below = int(
math.ceil(
abs(
stft.hertz2bin((1.0 - defs.B_PEAK_SPREAD_BELOW_HERTZ) *
base_frequency_estimate, sample_rate) -
bin_initial_estimate)))
bin_spread_above = int(
math.ceil(
stft.hertz2bin((1.0 + defs.B_PEAK_SPREAD_ABOVE_HERTZ) *
base_frequency_estimate, sample_rate) -
bin_initial_estimate))
#bin_spread_below = int(round(bin_initial_estimate *
# defs.B_PEAK_SPREAD_BELOW_HERTZ))
#bin_spread_above = int(round(bin_initial_estimate *
# defs.B_PEAK_SPREAD_BELOW_HERTZ))
#bin_spread_below_main = int(
# stft.hertz2bin(defs.STFT_PEAK_SPREAD_BELOW_HERTZ*base_frequency_estimate,
# sample_rate))
#bin_spread_above_main = int(
# stft.hertz2bin(defs.STFT_PEAK_SPREAD_ABOVE_HERTZ*base_frequency_estimate,
# sample_rate))
### actual estimate
bin_f0, B, rsquared, harmonics, limit = get_bin_f0_B(
bin_initial_estimate,
estimate_B_buffers,
noise_cutoff,
#estimate_B_buffers, numpy.zeros(defs.LONG_WINDOWSIZE+1),
bin_spread_below,
bin_spread_above,
sample_rate)
highest_harmonic = 0
for h in harmonics:
if highest_harmonic < h.n:
highest_harmonic = h.n
limit = min(limit, highest_harmonic)
# HACK: remove limit
#limit = defs.TOTAL_HARMONICS
#print "limit to:", limit
#harmonics_enable = [True]*defs.TOTAL_HARMONICS
harmonics_enable = [True] * limit
bins_estimate = [
partials.mode_B2freq(bin_f0, i, B)
for i in range(1,
len(harmonics_enable) + 1)
]
bins_naive = [i * bin_f0 for i in range(1, len(harmonics_enable) + 1)]
if defs.B_PLOT:
pylab.figure()
pylab.plot(initial_noise_freqs,
stft.amplitude2db(initial_noise_floor),
color='black')
#pylab.plot(initial_noise_freqs,
# stft.amplitude2db(initial_noise_floor)+defs.B_MINIMUM_HARMONIC_SNR,
# color='black')
pylab.xlabel("Frequency (seconds)")
pylab.ylabel("Power (/ dB)")
for i in range(estimate_B_buffers.shape[0]):
#color = matplotlib.cm.spring(float(wav_i)/len(filenames))
#color = matplotlib.cm.RdYlGn(
#color = matplotlib.cm.spring(
# float(i)/len(estimate_B_buffers_this_list))
pylab.plot(
freqs,
stft.amplitude2db(estimate_B_buffers[i, :]),
#color=color,
color="orange",
alpha=0.5,
label=basename,
)
for est in bins_estimate:
low = stft.bin2hertz(est - bin_spread_below, sample_rate)
high = stft.bin2hertz(est + bin_spread_above, sample_rate)
if True:
pylab.axvspan(low, high, color='c', alpha=0.3)
else:
pylab.axvline(
stft.bin2hertz(est, sample_rate),
color='cyan',
alpha=0.3,
#linewidth=2.0
)
for naive in bins_naive:
freq = stft.bin2hertz(naive, sample_rate)
pylab.axvline(
freq,
color='grey',
alpha=0.2,
#linewidth=2.0
)
for j, harm in enumerate(harmonics):
if harm.mag == 0:
continue
fn = stft.bin2hertz(harm.fft_bin, sample_rate)
mag = stft.amplitude2db(harm.mag)
#pylab.plot(fn, mag, 'o',
# color='green'
# )
pylab.xlabel("Frequency")
pylab.ylabel("Decibels")
if defs.B_DUMP_HARMS:
t_fns = []
t_mags = []
for j, harm in enumerate(harmonics):
if harm.mag == 0:
continue
fn = stft.bin2hertz(harm.fft_bin, sample_rate)
mag = stft.amplitude2db(harm.mag)
t_fns.append(fn)
t_mags.append(mag)
data = numpy.vstack((t_fns, t_mags)).transpose()
numpy.savetxt("B-harms.txt", data)
if defs.B_PLOT:
pylab.show()
f0 = stft.bin2hertz(bin_f0, sample_rate)
stiff_ideal_limit = stiff_ideal_conflict.find_limit(
bin_f0, B, bin_spread_below, bin_spread_above)
lim = min(stiff_ideal_limit, limit)
detected_freqs = StringFreqsB(f0, B, lim)
stats = StringFreqsB_stats()
stats.num_files = len(filenames)
stats.rsquared = rsquared
stats.highest_mode_detected = limit
stats.highest_mode_stiff_ideal = stiff_ideal_limit
stats.basename = basename
adjusted_B, delta_fn = adjust_B.adjust(basename, limit, f0, B)
if adjusted_B is not None:
stiff_ideal_lim_adjusted = stiff_ideal_conflict.find_limit(
bin_f0, adjusted_B, bin_spread_below, bin_spread_above)
lim = min(stiff_ideal_lim_adjusted, limit)
adjusted_freqs = StringFreqsB(f0, adjusted_B, lim)
adjusted_freqs.delta_fn = delta_fn
stats.highest_mode_stiff_ideal_adjusted = stiff_ideal_lim_adjusted
stats.delta_fn = delta_fn
final = StringFreqsB(
f0, adjusted_B,
min(stats.highest_mode_detected, stats.highest_mode_stiff_ideal,
stiff_ideal_lim_adjusted))
else:
adjusted_freqs = None
final = StringFreqsB(
f0, B,
min(stats.highest_mode_detected, stats.highest_mode_stiff_ideal))
return detected_freqs, adjusted_freqs, stats, final
