def main(argv):
if len(argv) != 2:
print "usage: python %s foo.mp3" % (argv[0])
return
fp = FeaturePlan(sample_rate=SAMPLE_RATE, resample=True, time_start=TIME_START, time_limit=TIME_LIMIT)
fp.addFeature("frames: Frames blockSize={0} stepSize={1}".format(SLICE_WINSIZE, SLICE_STEPSIZE))
if "YAAFE_PATH" in os.environ:
fp.addFeature(
"beat_hist: BeatHistogramSummary ACPNbPeaks=3 BHSBeatFrameSize=128 BHSBeatFrameStep=64 "
"BHSHistogramFrameSize=40 BHSHistogramFrameStep=40 FFTLength=0 FFTWindow=Hanning "
"HInf=40 HNbBins=80 HSup=200 NMANbFrames=5000 blockSize=1024 stepSize=512"
)
df = fp.getDataFlow()
engine = Engine()
engine.load(df)
afp = AudioFileProcessor()
song_path = argv[1]
assert os.path.exists(song_path)
afp.processFile(engine, song_path)
frames = engine.readOutput("frames")
frames = np.concatenate(frames)
print "time start: %ss" % TIME_START
print "time limit: %ss" % TIME_LIMIT
print "duration:", 1.0 * frames.size / SAMPLE_RATE
if "YAAFE_PATH" in os.environ:
beat_hist = engine.readOutput("beat_hist")
print "beat_hist: %s" % beat_hist
def main(argv):
if len(argv) != 2:
print 'usage: python %s foo.mp3' % (argv[0])
return
fp = FeaturePlan(sample_rate=SAMPLE_RATE,
resample=True,
time_start=TIME_START,
time_limit=TIME_LIMIT)
fp.addFeature("frames: Frames blockSize={0} stepSize={1}".format(
SLICE_WINSIZE, SLICE_STEPSIZE))
if 'YAAFE_PATH' in os.environ:
fp.addFeature(
"beat_hist: BeatHistogramSummary ACPNbPeaks=3 BHSBeatFrameSize=128 BHSBeatFrameStep=64 "
"BHSHistogramFrameSize=40 BHSHistogramFrameStep=40 FFTLength=0 FFTWindow=Hanning "
"HInf=40 HNbBins=80 HSup=200 NMANbFrames=5000 blockSize=1024 stepSize=512"
)
df = fp.getDataFlow()
engine = Engine()
engine.load(df)
afp = AudioFileProcessor()
song_path = argv[1]
assert os.path.exists(song_path)
afp.processFile(engine, song_path)
frames = engine.readOutput('frames')
frames = np.concatenate(frames)
print 'time start: %ss' % TIME_START
print 'time limit: %ss' % TIME_LIMIT
print 'duration:', 1. * frames.size / SAMPLE_RATE
if 'YAAFE_PATH' in os.environ:
beat_hist = engine.readOutput('beat_hist')
print 'beat_hist: %s' % beat_hist
def compute_spec(song_path):
fp = FeaturePlan(sample_rate=22050, resample=True)
#add one feature
fp.addFeature("spec: PowerSpectrum blockSize=1024 stepSize=512")
df = fp.getDataFlow()
engine = Engine()
engine.load(df)
afp = AudioFileProcessor()
afp.processFile(engine, song_path)
return engine.readOutput('spec')
def compute_spec(song_path):
fp = FeaturePlan(sample_rate=22050, resample=True)
#add one feature
fp.addFeature("spec: PowerSpectrum blockSize=1024 stepSize=512")
df = fp.getDataFlow()
engine = Engine()
engine.load(df)
afp = AudioFileProcessor()
afp.processFile(engine, song_path)
return engine.readOutput('spec')
def main(argv):
if len(argv) != 2:
print 'usage: python %s foo.mp3' % (argv[0])
return
fp = FeaturePlan(sample_rate=SAMPLE_RATE, resample=True, time_start=TIME_START, time_limit=TIME_LIMIT)
fp.addFeature("frames: Frames blockSize={0} stepSize={1}".format(
SLICE_WINSIZE, SLICE_STEPSIZE))
df = fp.getDataFlow()
engine = Engine()
engine.load(df)
afp = AudioFileProcessor()
song_path = argv[1]
assert os.path.exists(song_path)
afp.processFile(engine, song_path)
frames = engine.readOutput('frames')
frames = np.concatenate(frames)
print 'time start: %ss' % TIME_START
print 'time limit: %ss' % TIME_LIMIT
print 'duration:', 1. * frames.size / SAMPLE_RATE
from pylab import plot, show
plot(frames)
show()
def detect(wav_path, ans_path=None):
sample_rate = 8000
block_size = 1024
step_size = block_size / 2
n_band = block_size / 2
freq_bound = [i * sample_rate / 2. / n_band for i in range(n_band + 1)]
plan = FeaturePlan(sample_rate=sample_rate, resample=True)
plan.addFeature('power_spectrum: PowerSpectrum blockSize=%d stepSize=%d' %
(block_size, step_size))
dataflow = plan.getDataFlow()
afp = AudioFileProcessor()
engine = Engine()
engine.load(dataflow)
afp.processFile(engine, wav_path)
spectrogram = engine.readOutput('power_spectrum')
seq = []
for spectrum in spectrogram:
mean_mag = np.mean(spectrum)
if mean_mag <= SILENT_MAG_THRESHOLD:
seq.append(SILENT_KEY)
continue
lower_data = (-1, -1)
upper_data = (-1, -1)
for target_idx, target_freq in itertools.chain(enumerate(LOWER_FREQS),
enumerate(UPPER_FREQS)):
idx = bisect.bisect(freq_bound, target_freq)
assert idx > 0
freq1 = freq_bound[idx - 1]
mag1 = spectrum[idx - 1]
freq2 = freq_bound[idx]
mag2 = spectrum[idx]
w1 = 1. * (freq2 - target_freq) / (freq2 - freq1)
w2 = 1. - w1
target_mag = (w1 * mag1 + w2 * mag2)
if target_mag > mean_mag * 2:
if target_freq < 1000:
if target_mag > lower_data[1]:
lower_data = (target_idx, target_mag)
else:
if target_mag > upper_data[1]:
upper_data = (target_idx, target_mag)
lower_idx = lower_data[0]
upper_idx = upper_data[0]
if lower_idx == -1 or upper_idx == -1:
seq.append(UNKNOWN_KEY)
else:
seq.append(KEYS[lower_idx * len(LOWER_FREQS) + upper_idx])
ans = purge_seq(seq)
if ans_path is not None:
with open(ans_path) as fh:
for i, line in enumerate(fh):
line = line.strip()
assert line == ans[i], "%s != %s" % (line, ans[i])
print '[%d] %s' % (i, line)
else:
for i, line in enumerate(ans):
print '[%d] %s' % (i, line)
def detect(wav_path, ans_path=None):
sample_rate = 8000
block_size = 1024
step_size = block_size / 2
n_band = block_size / 2
freq_bound = [i * sample_rate / 2. / n_band for i in range(n_band + 1)]
plan = FeaturePlan(sample_rate=sample_rate, resample=True)
plan.addFeature(
'power_spectrum: PowerSpectrum blockSize=%d stepSize=%d' % (
block_size, step_size
)
)
dataflow = plan.getDataFlow()
afp = AudioFileProcessor()
engine = Engine()
engine.load(dataflow)
afp.processFile(engine, wav_path)
spectrogram = engine.readOutput('power_spectrum')
seq = []
for spectrum in spectrogram:
mean_mag = np.mean(spectrum)
if mean_mag <= SILENT_MAG_THRESHOLD:
seq.append(SILENT_KEY)
continue
lower_data = (-1, -1)
upper_data = (-1, -1)
for target_idx, target_freq in itertools.chain(
enumerate(LOWER_FREQS), enumerate(UPPER_FREQS)
):
idx = bisect.bisect(freq_bound, target_freq)
assert idx > 0
freq1 = freq_bound[idx - 1]
mag1 = spectrum[idx - 1]
freq2 = freq_bound[idx]
mag2 = spectrum[idx]
w1 = 1. * (freq2 - target_freq) / (freq2 - freq1)
w2 = 1. - w1
target_mag = (w1 * mag1 + w2 * mag2)
if target_mag > mean_mag * 2:
if target_freq < 1000:
if target_mag > lower_data[1]:
lower_data = (target_idx, target_mag)
else:
if target_mag > upper_data[1]:
upper_data = (target_idx, target_mag)
lower_idx = lower_data[0]
upper_idx = upper_data[0]
if lower_idx == -1 or upper_idx == -1:
seq.append(UNKNOWN_KEY)
else:
seq.append(KEYS[lower_idx * len(LOWER_FREQS) + upper_idx])
ans = purge_seq(seq)
if ans_path is not None:
with open(ans_path) as fh:
for i, line in enumerate(fh):
line = line.strip()
assert line == ans[i], "%s != %s" % (line, ans[i])
print '[%d] %s' % (i, line)
else:
for i, line in enumerate(ans):
print '[%d] %s' % (i, line)
