def _wav_write(signal, wav_name, sample_rate):
"""
::
Utility routine for writing wav files, use scikits.audiolab if available
"""
if HAVE_AUDIOLAB:
scikits.audiolab.wavwrite(signal, wav_name, sample_rate)
else:
signal = numpy.atleast_2d(signal)
w = wave.Wave_write(wav_name)
if not w:
print("Error opening file named: ", wav_name)
raise error.BregmanError()
w.setparams(
(signal.shape[0], 2, sample_rate, signal.shape[1], 'NONE', 'NONE'))
b_signal = '' # C-style binary string
for i in range(signal.shape[1]):
# transform to C-style binary string
b_signal += wave.struct.pack('h', int(32767 * signal[0, i]))
if signal.shape[0] > 1:
# transform to C-style binary string
b_signal += wave.struct.pack('h', int(32767 * signal[1, i]))
w.writeframes(b_signal)
w.close()
return True
def insert_audio_files(fileList, dbName, chroma=True, mfcc=False, cqft=False, progress=None):
"""
::
Simple insert features into an audioDB database named by dbBame.
Features are either chroma [default], mfcc, or cqft.
Feature parameters are default.
"""
db = adb.get(dbName, "w")
if not db:
print ("Could not open database: %s" %dbName)
return False
del db # commit the changes by closing the header
db = adb.get(dbName) # re-open for writing data
# FIXME: need to test if KEY (%i) already exists in db
# Support for removing keys via include/exclude keys
for a, i in enumerate(fileList):
if progress:
progress((a+0.5)/float(len(fileList)),i) # frac, fname
print ("Processing file: %s" %i)
F = features.Features(i)
if chroma: F.feature_params['feature']='chroma'
elif mfcc: F.feature_params['feature']='mfcc'
elif cqft: F.feature_params['feature']='cqft'
else:
raise error.BregmanError("One of chroma, mfcc, or cqft must be specified for features")
F.extract()
# raw features and power in Bels
if progress:
progress((a+1.0)/float(len(fileList)),i) # frac, fname
db.insert(featData=F.CHROMA.T, powerData=adb.feature_scale(F.POWER, bels=True), key=i)
# db.insert(featData=F.CHROMA.T, powerData=F.feature_scale(F.POWER, bels=True), key=i)
return db
def _istftm(self,
X_hat=None,
Phi_hat=None,
pvoc=False,
usewin=True,
resamp=None):
"""
::
Inverse short-time Fourier transform magnitude. Make a signal from a |STFT| transform.
Uses phases from self.STFT if Phi_hat is None.
Inputs:
X_hat - N/2+1 magnitude STFT [None=abs(self.STFT)]
Phi_hat - N/2+1 phase STFT [None=exp(1j*angle(self.STFT))]
pvoc - whether to use phase vocoder [False]
usewin - whether to use overlap-add [False]
Returns:
x_hat - estimated signal
"""
if not self._have_stft:
return None
X_hat = self.X if X_hat is None else P.np.abs(X_hat)
if pvoc:
self._pvoc(X_hat, Phi_hat, pvoc)
else:
Phi_hat = P.angle(self.STFT) if Phi_hat is None else Phi_hat
self.X_hat = X_hat * P.exp(1j * Phi_hat)
if usewin:
if self.win is None:
self.win = P.ones(
self.wfft) if self.window == 'rect' else P.np.sqrt(
P.hanning(self.wfft))
if len(self.win) != self.nfft:
self.win = P.r_[self.win, P.np.zeros(self.nfft - self.wfft)]
if len(self.win) != self.nfft:
error.BregmanError(
"features_base.Features._istftm(): assertion failed len(self.win)==self.nfft"
)
else:
self.win = P.ones(self.nfft)
if resamp:
self.win = sig.resample(self.win,
int(P.np.round(self.nfft * resamp)))
fp = self._check_feature_params()
self.x_hat = self._overlap_add(P.real(P.irfft(self.X_hat.T)),
usewin=usewin,
resamp=resamp)
if self.verbosity:
print("Extracted iSTFTM->self.x_hat")
return self.x_hat
def play_snd(data, sample_rate=44100):
"""
::
Bregman Linux/OSX/Windows sound player function.
data - a numpy array
sample_rate - default 44100
"""
m = abs(data).max() + 0.001
if m > 1.0: data /= m
_wav_write(data, AUDIO_TMP_FILE, sample_rate)
command = [sound_options['soundplayer'], AUDIO_TMP_FILE]
res = subprocess.call(command)
if res:
raise error.BregmanError("Error in " + command[0])
return res
def _extract_error(self):
error.BregmanError("unrecognized feature in Features.extract()")