def onset_strength(y=None,
sr=22050,
S=None,
detrend=False,
centering=True,
feature=None,
aggregate=None,
**kwargs):
"""Compute a spectral flux onset strength envelope.
Onset strength at time t is determined by:
``mean_f max(0, S[f, t+1] - S[f, t])``
By default, if a time series ``y`` is provided, S will be the
log-power Mel spectrogram.
:usage:
>>> # Mean aggregation with Mel-scaled spectrogram
>>> o_env = librosa.onset.onset_strength(y, sr)
>>> # Median aggregation
>>> o_env = librosa.onset.onset_strength(y, sr,
aggregate=np.median)
>>> # Log-frequency spectrogram instead of Mel
>>> o_env = librosa.onset.onset_strength(y, sr,
feature=librosa.feature.logfsgram)
>>> # Or Mel spectrogram with customized options
>>> o_env = librosa.onset.onset_strength(y, sr,
n_mels=128,
fmin=32,
fmax=8000)
:parameters:
- y : np.ndarray [shape=(n,)]
audio time-series
- sr : int > 0 [scalar]
sampling rate of ``y``
- S : np.ndarray [shape=(d, m)]
pre-computed (log-power) spectrogram
- detrend : bool [scalar]
Filter the onset strength to remove the DC component
- centering : bool [scalar]
Shift the onset function by ``n_fft / (2 * hop_length)`` frames
- feature : function
Function for computing time-series features, eg, scaled spectrograms.
By default, uses :func:`librosa.feature.melspectrogram`
- aggregate : function
Aggregation function to use when combining onsets
at different frequency bins.
Default: ``np.mean``
- *kwargs*
Additional parameters to ``feature()``, if ``S`` is not provided.
.. note:: if ``S`` is provided, then ``(y, sr)`` are optional.
:returns:
- onset_envelope : np.ndarray [shape=(m,)]
vector containing the onset strength envelope
:raises:
- ValueError
if neither ``(y, sr)`` nor ``S`` are provided
"""
if feature is None:
feature = librosa.feature.melspectrogram
if aggregate is None:
aggregate = np.mean
# First, compute mel spectrogram
if S is None:
if y is None:
raise ValueError('One of "S" or "y" must be provided.')
S = np.abs(feature(y=y, sr=sr, **kwargs))
# Convert to dBs
S = librosa.core.logamplitude(S)
# Retrieve the n_fft and hop_length,
# or default values for onsets if not provided
n_fft = kwargs.get('n_fft', 2048)
hop_length = kwargs.get('hop_length', 64)
# Compute first difference, include padding for alignment purposes
onset_env = np.diff(S, axis=1)
onset_env = np.pad(onset_env, ([0, 0], [1, 0]), mode='constant')
# Discard negatives (decreasing amplitude)
onset_env = np.maximum(0.0, onset_env)
# Average over mel bands
onset_env = aggregate(onset_env, axis=0)
# Counter-act framing effects. Shift the onsets by n_fft / hop_length
if centering:
onset_env = np.pad(onset_env, (int(n_fft / (2 * hop_length)), 0),
mode='constant')
# remove the DC component
if detrend:
onset_env = scipy.signal.lfilter([1.0, -1.0], [1.0, -0.99], onset_env)
return onset_env
def onset_strength(y=None, sr=22050, S=None, detrend=False, centering=True,
feature=None, aggregate=None, **kwargs):
"""Compute a spectral flux onset strength envelope.
Onset strength at time t is determined by:
``mean_f max(0, S[f, t+1] - S[f, t])``
By default, if a time series ``y`` is provided, S will be the
log-power Mel spectrogram.
:usage:
>>> # Mean aggregation with Mel-scaled spectrogram
>>> o_env = librosa.onset.onset_strength(y, sr)
>>> # Median aggregation
>>> o_env = librosa.onset.onset_strength(y, sr,
aggregate=np.median)
>>> # Log-frequency spectrogram instead of Mel
>>> o_env = librosa.onset.onset_strength(y, sr,
feature=librosa.feature.logfsgram)
>>> # Or Mel spectrogram with customized options
>>> o_env = librosa.onset.onset_strength(y, sr,
n_mels=128,
fmin=32,
fmax=8000)
:parameters:
- y : np.ndarray
audio time-series
- sr : int
sampling rate of ``y``
- S : np.ndarray
pre-computed (log-power) spectrogram
- detrend : bool
Filter the onset strength to remove the DC component
- centering : bool
Shift the onset function by ``n_fft / (2 * hop_length)`` frames
- feature : function
Function for computing time-series features, eg, scaled spectrograms.
By default, uses ``librosa.feature.melspectrogram``
- aggregate : function
Aggregation function to use when combining onsets
at different frequency bins.
Default: ``np.mean``
- *kwargs*
Additional parameters to ``feature()``, if ``S`` is not provided.
.. note:: if ``S`` is provided, then ``(y, sr)`` are optional.
:returns:
- onset_envelope : np.ndarray
vector containing the onset strength envelope
:raises:
- ValueError
if neither ``(y, sr)`` nor ``S`` are provided
"""
if feature is None:
feature = librosa.feature.melspectrogram
if aggregate is None:
aggregate = np.mean
# First, compute mel spectrogram
if S is None:
if y is None:
raise ValueError('One of "S" or "y" must be provided.')
S = np.abs(feature(y=y, sr=sr, **kwargs))
# Convert to dBs
S = librosa.core.logamplitude(S)
# Retrieve the n_fft and hop_length,
# or default values for onsets if not provided
n_fft = kwargs.get('n_fft', 2048)
hop_length = kwargs.get('hop_length', 64)
# Compute first difference, include padding for alignment purposes
onset_env = np.diff(S, axis=1)
onset_env = np.pad(onset_env, ([0, 0], [1, 0]), mode='constant')
# Discard negatives (decreasing amplitude)
onset_env = np.maximum(0.0, onset_env)
# Average over mel bands
onset_env = aggregate(onset_env, axis=0)
# Counter-act framing effects. Shift the onsets by n_fft / hop_length
if centering:
onset_env = np.pad(onset_env,
(n_fft / (2 * hop_length), 0),
mode='constant')
# remove the DC component
if detrend:
onset_env = scipy.signal.lfilter([1.0, -1.0], [1.0, -0.99], onset_env)
return onset_env
def onset_strength(
y=None, sr=22050, S=None, detrend=False, feature=librosa.feature.melspectrogram, aggregate=np.mean, **kwargs
):
"""Spectral flux onset strength.
Onset strength at time t is determined by:
``mean_f max(0, S[f, t+1] - S[f, t])``
By default, if a time series is provided, S will be the log-power Mel spectrogram.
:usage:
>>> # Mean aggregation with Mel-scaled spectrogram
>>> onsets = librosa.onset.onset_strength(y, sr)
>>> # Median aggregation
>>> onsets = librosa.onset.onset_strength(y, sr, aggregate=np.median)
>>> # Log-frequency spectrogram instead of Mel
>>> onsets = librosa.onset.onset_strength(y, sr, feature=librosa.feature.logfsgram)
>>> # Or Mel spectrogram with customized options
>>> onsets = librosa.onset.onset_strength(y, sr, n_mels=128, fmin=32, fmax=8000)
:parameters:
- y : np.ndarray
audio time-series
- sr : int
sampling rate of ``y``
- S : np.ndarray
pre-computed (log-power) spectrogram
- detrend : bool
Filter the onset strength to remove
- feature : function
Function for computing time-series features, eg, scaled spectrograms.
By default, uses ``librosa.feature.melspectrogram``
- aggregate : function
Aggregation function to use when combining onsets
at different frequency bins.
- kwargs
Parameters to ``feature()``, if ``S`` is not provided.
.. note:: if ``S`` is provided, then ``(y, sr)`` are optional.
:returns:
- onsets : np.ndarray
vector of onset strengths
:raises:
- ValueError
if neither ``(y, sr)`` nor ``S`` are provided
"""
# First, compute mel spectrogram
if S is None:
if y is None:
raise ValueError('One of "S" or "y" must be provided.')
S = np.abs(feature(y=y, sr=sr, **kwargs))
# Convert to dBs
S = librosa.core.logamplitude(S)
# Compute first difference
onsets = np.diff(S, n=1, axis=1)
# Discard negatives (decreasing amplitude)
onsets = np.maximum(0.0, onsets)
# Average over mel bands
onsets = aggregate(onsets, axis=0)
# remove the DC component
if detrend:
onsets = scipy.signal.lfilter([1.0, -1.0], [1.0, -0.99], onsets)
return onsets
