}Kg T NdZddlZddlZddlmZddlmZddlmZddl m Z ddl m Z dd l mZmZmZmZmZmZgd Zdd dd d ddddd deej*dedeej*dededeej*dededededej*fdZdd ddddd dddd deej*dedeej*ded ed!eej*d"ed#ed$eed%eeeefdedej*fd&Zd'ej*dej*dej*fd(Zed)*dd dd+d dddd ddddd, deej*dedeej*d-ededed ed!eej*d"ed#ed$eed%eeeefd.eeeeeefdedej*fd/Zy)0z Onset detection =============== .. autosummary:: :toctree: generated/ onset_detect onset_backtrack onset_strength onset_strength_multi N)cache)core)util)ParameterError)melspectrogram)AnyCallableIterableOptionalUnionSequence) onset_detectonset_strengthonset_strength_multionset_backtracki"ViFframesT) ysronset_envelope hop_length backtrackenergyunits normalizesparserrrrrrrrrkwargsreturnc  || tdt|||}|rL|tj|ddz }|tj|ddt j |zz}|J|jr(tjtj|s:|rtjgt} ntj|t} n| jdd|z|z| jd d |z|zd z| jd d |z|z| jdd |z|zd z| jdd|z|z| jddt j|f|dd| } |r!|s td||}|Jt!| |} |rS|dk(r | S|dk(rt#j$| |} | S|dk(rt#j&| ||} | Std|| S)aLocate note onset events by picking peaks in an onset strength envelope. The `peak_pick` parameters were chosen by large-scale hyper-parameter optimization over the dataset provided by [#]_. .. [#] https://github.com/CPJKU/onset_db Parameters ---------- y : np.ndarray [shape=(..., n)] audio time-series. Multi-channel is supported. sr : number > 0 [scalar] sampling rate of ``y`` onset_envelope : np.ndarray [shape=(..., m)] (optional) pre-computed onset strength envelope hop_length : int > 0 [scalar] hop length (in samples) units : {'frames', 'samples', 'time'} The units to encode detected onset events in. By default, 'frames' are used. backtrack : bool If ``True``, detected onset events are backtracked to the nearest preceding minimum of ``energy``. This is primarily useful when using onsets as slice points for segmentation. .. note:: backtracking is only supported if ``sparse=True``. energy : np.ndarray [shape=(m,)] (optional) An energy function to use for backtracking detected onset events. If none is provided, then ``onset_envelope`` is used. normalize : bool If ``True`` (default), normalize the onset envelope to have minimum of 0 and maximum of 1 prior to detection. This is helpful for standardizing the parameters of `librosa.util.peak_pick`. Otherwise, the onset envelope is left unnormalized. sparse : bool If ``True`` (default), detections are returned as an array of frames, samples, or time indices (as specified by ``units=``). If ``False``, detections are encoded as a dense boolean array where ``onsets[n]`` is True if there's an onset at frame index ``n``. .. note:: multi-channel input is only supported if ``sparse=False``. **kwargs : additional keyword arguments Additional parameters for peak picking. See `librosa.util.peak_pick` for details. Returns ------- onsets : np.ndarray [shape=(n_onsets,) or onset_envelope.shape] estimated positions of detected onsets, in whichever units are specified. By default, frame indices. If `sparse=False`, `onsets[..., n]` indicates an onset detection at frame index `n`. .. note:: If no onset strength could be detected, onset_detect returns an empty array (sparse=True) or all-False array (sparse=False). Raises ------ ParameterError if neither ``y`` nor ``onsets`` are provided or if ``units`` is not one of 'frames', 'samples', or 'time' See Also -------- onset_strength : compute onset strength per-frame onset_backtrack : backtracking onset events librosa.util.peak_pick : pick peaks from a time series Examples -------- Get onset times from a signal >>> y, sr = librosa.load(librosa.ex('trumpet')) >>> librosa.onset.onset_detect(y=y, sr=sr, units='time') array([0.07 , 0.232, 0.395, 0.604, 0.743, 0.929, 1.045, 1.115, 1.416, 1.672, 1.881, 2.043, 2.206, 2.368, 2.554, 3.019]) Or use a pre-computed onset envelope >>> o_env = librosa.onset.onset_strength(y=y, sr=sr) >>> times = librosa.times_like(o_env, sr=sr) >>> onset_frames = librosa.onset.onset_detect(onset_envelope=o_env, sr=sr) >>> import matplotlib.pyplot as plt >>> D = np.abs(librosa.stft(y)) >>> fig, ax = plt.subplots(nrows=2, sharex=True) >>> librosa.display.specshow(librosa.amplitude_to_db(D, ref=np.max), ... x_axis='time', y_axis='log', ax=ax[0]) >>> ax[0].set(title='Power spectrogram') >>> ax[0].label_outer() >>> ax[1].plot(times, o_env, label='Onset strength') >>> ax[1].vlines(times[onset_frames], 0, o_env.max(), color='r', alpha=0.9, ... linestyle='--', label='Onsets') >>> ax[1].legend() z$y or onset_envelope must be provided)rrrT)keepdimsaxis)dtypepre_maxgQ?post_maxrpre_avgg?post_avgwaitdeltagQ?)rr"z3onset backtracking is only supported if sparse=Truersamples)rtime)rrzInvalid unit type: )rrnpminmaxrtinyanyallisfinitearrayint zeros_likebool setdefault peak_pickrrframes_to_samplesframes_to_time) rrrrrrrrrronsetss Q/home/alanp/www/video.onchill/myenv/lib/python3.12/site-packages/librosa/onset.pyrrs%z 9 !GH H'!zJ("&&$UW*XX "&&$RH499UcKddd  %% %    rvvbkk..I'J XXb,F]]>>F )TBY*%<=*dRi:&=&AB)TBY*%<=*dRi:&=&AB&$)z"9:'4(QvBQ&Q $%Z[[~'% %%$VV4F H   Mi ++FzJF M f_((J2NF M!#6ug!>? ? M) rrSlagmax_sizerefdetrendcenterfeature aggregater?r@rArBrCrDrErFc  b| dur tdtd|||||||||| dd | } | ddddfS)uCompute a spectral flux onset strength envelope. Onset strength at time ``t`` is determined by:: mean_f max(0, S[f, t] - ref[f, t - lag]) where ``ref`` is ``S`` after local max filtering along the frequency axis [#]_. By default, if a time series ``y`` is provided, S will be the log-power Mel spectrogram. .. [#] Böck, Sebastian, and Gerhard Widmer. "Maximum filter vibrato suppression for onset detection." 16th International Conference on Digital Audio Effects, Maynooth, Ireland. 2013. Parameters ---------- y : np.ndarray [shape=(..., n)] audio time-series. Multi-channel is supported. sr : number > 0 [scalar] sampling rate of ``y`` S : np.ndarray [shape=(..., d, m)] pre-computed (log-power) spectrogram lag : int > 0 time lag for computing differences max_size : int > 0 size (in frequency bins) of the local max filter. set to `1` to disable filtering. ref : None or np.ndarray [shape=(..., d, m)] An optional pre-computed reference spectrum, of the same shape as ``S``. If not provided, it will be computed from ``S``. If provided, it will override any local max filtering governed by ``max_size``. detrend : bool [scalar] Filter the onset strength to remove the DC component center : bool [scalar] Shift the onset function by ``n_fft // (2 * hop_length)`` frames. This corresponds to using a centered frame analysis in the short-time Fourier transform. feature : function Function for computing time-series features, eg, scaled spectrograms. By default, uses `librosa.feature.melspectrogram` with ``fmax=sr/2`` aggregate : function Aggregation function to use when combining onsets at different frequency bins. Default: `np.mean` **kwargs : additional keyword arguments Additional parameters to ``feature()``, if ``S`` is not provided. Returns ------- onset_envelope : np.ndarray [shape=(..., m,)] vector containing the onset strength envelope. If the input contains multiple channels, then onset envelope is computed for each channel. Raises ------ ParameterError if neither ``(y, sr)`` nor ``S`` are provided or if ``lag`` or ``max_size`` are not positive integers See Also -------- onset_detect onset_strength_multi Examples -------- First, load some audio and plot the spectrogram >>> import matplotlib.pyplot as plt >>> y, sr = librosa.load(librosa.ex('trumpet'), duration=3) >>> D = np.abs(librosa.stft(y)) >>> times = librosa.times_like(D, sr=sr) >>> fig, ax = plt.subplots(nrows=2, sharex=True) >>> librosa.display.specshow(librosa.amplitude_to_db(D, ref=np.max), ... y_axis='log', x_axis='time', ax=ax[0]) >>> ax[0].set(title='Power spectrogram') >>> ax[0].label_outer() Construct a standard onset function >>> onset_env = librosa.onset.onset_strength(y=y, sr=sr) >>> ax[1].plot(times, 2 + onset_env / onset_env.max(), alpha=0.8, ... label='Mean (mel)') Median aggregation, and custom mel options >>> onset_env = librosa.onset.onset_strength(y=y, sr=sr, ... aggregate=np.median, ... fmax=8000, n_mels=256) >>> ax[1].plot(times, 1 + onset_env / onset_env.max(), alpha=0.8, ... label='Median (custom mel)') Constant-Q spectrogram instead of Mel >>> C = np.abs(librosa.cqt(y=y, sr=sr)) >>> onset_env = librosa.onset.onset_strength(sr=sr, S=librosa.amplitude_to_db(C, ref=np.max)) >>> ax[1].plot(times, onset_env / onset_env.max(), alpha=0.8, ... label='Mean (CQT)') >>> ax[1].legend() >>> ax[1].set(ylabel='Normalized strength', yticks=[]) FzPaggregate parameter cannot be False when computing full-spectrum onset strength.N) rrr?r@rArBrCrDrErFchannels.r)rr) rrr?r@rArBrCrDrErFrodf_alls r=rrslDE^  #      G 319 r>eventsctj|dd|ddk|dd|ddkz}tjd|zd}|tj||d }|S) a Backtrack detected onset events to the nearest preceding local minimum of an energy function. This function can be used to roll back the timing of detected onsets from a detected peak amplitude to the preceding minimum. This is most useful when using onsets to determine slice points for segmentation, as described by [#]_. .. [#] Jehan, Tristan. "Creating music by listening" Doctoral dissertation Massachusetts Institute of Technology, 2005. Parameters ---------- events : np.ndarray, dtype=int List of onset event frame indices, as computed by `onset_detect` energy : np.ndarray, shape=(m,) An energy function Returns ------- events_backtracked : np.ndarray, shape=events.shape The input events matched to nearest preceding minima of ``energy``. Examples -------- Backtrack the events using the onset envelope >>> y, sr = librosa.load(librosa.ex('trumpet'), duration=3) >>> oenv = librosa.onset.onset_strength(y=y, sr=sr) >>> times = librosa.times_like(oenv, sr=sr) >>> # Detect events without backtracking >>> onset_raw = librosa.onset.onset_detect(onset_envelope=oenv, ... backtrack=False) >>> onset_bt = librosa.onset.onset_backtrack(onset_raw, oenv) Backtrack the events using the RMS values >>> S = np.abs(librosa.stft(y=y)) >>> rms = librosa.feature.rms(S=S) >>> onset_bt_rms = librosa.onset.onset_backtrack(onset_raw, rms[0]) Plot the results >>> import matplotlib.pyplot as plt >>> fig, ax = plt.subplots(nrows=3, sharex=True) >>> librosa.display.specshow(librosa.amplitude_to_db(S, ref=np.max), ... y_axis='log', x_axis='time', ax=ax[0]) >>> ax[0].label_outer() >>> ax[1].plot(times, oenv, label='Onset strength') >>> ax[1].vlines(librosa.frames_to_time(onset_raw), 0, oenv.max(), label='Raw onsets') >>> ax[1].vlines(librosa.frames_to_time(onset_bt), 0, oenv.max(), label='Backtracked', color='r') >>> ax[1].legend() >>> ax[1].label_outer() >>> ax[2].plot(times, rms[0], label='RMS') >>> ax[2].vlines(librosa.frames_to_time(onset_bt_rms), 0, rms.max(), label='Backtracked (RMS)', color='r') >>> ax[2].legend() rr Nr)x_minF)right)r- flatnonzeror fix_frames match_events)rKrminimaresultss r=rrqsr@^^VAb\VCR[8VAb\FSTSUJ=VW XF__QZq 1F!!2!266!OPG Nr>)leveli) rrr?n_fftrr@rArBrCrDrErFrHrXrHc Z| t} | jdd|z| tj} t j |st d|dt j |st d|d|5tj| d||||d| }tj|}|Jtj|}|+|dk(r|}natjj||d }n>|j|jk7r%t d |jd |j|d |df|d d| fz }tjd|}d}| t!dg} nd}t#| rt j$|| | |d }|}| r ||d|zzz }|jDcgc]}d}}t'|df|d<tj(||d}|r'tj*j-ddgddg|d }| r|d d|jdf}|Scc}w)a Compute a spectral flux onset strength envelope across multiple channels. Onset strength for channel ``i`` at time ``t`` is determined by:: mean_{f in channels[i]} max(0, S[f, t+1] - S[f, t]) Parameters ---------- y : np.ndarray [shape=(..., n,)] audio time-series. Multi-channel is supported. sr : number > 0 [scalar] sampling rate of ``y`` S : np.ndarray [shape=(..., d, m)] pre-computed (log-power) spectrogram n_fft : int > 0 [scalar] FFT window size for use in ``feature()`` if ``S`` is not provided. hop_length : int > 0 [scalar] hop length for use in ``feature()`` if ``S`` is not provided. lag : int > 0 time lag for computing differences max_size : int > 0 size (in frequency bins) of the local max filter. set to `1` to disable filtering. ref : None or np.ndarray [shape=(d, m)] An optional pre-computed reference spectrum, of the same shape as ``S``. If not provided, it will be computed from ``S``. If provided, it will override any local max filtering governed by ``max_size``. detrend : bool [scalar] Filter the onset strength to remove the DC component center : bool [scalar] Shift the onset function by ``n_fft // (2 * hop_length)`` frames. This corresponds to using a centered frame analysis in the short-time Fourier transform. feature : function Function for computing time-series features, eg, scaled spectrograms. By default, uses `librosa.feature.melspectrogram` with ``fmax=sr/2`` Must support arguments: ``y, sr, n_fft, hop_length`` aggregate : function or False Aggregation function to use when combining onsets at different frequency bins. If ``False``, then no aggregation is performed. Default: `np.mean` channels : list or None Array of channel boundaries or slice objects. If `None`, then a single channel is generated to span all bands. **kwargs : additional keyword arguments Additional parameters to ``feature()``, if ``S`` is not provided. Returns ------- onset_envelope : np.ndarray [shape=(..., n_channels, m)] array containing the onset strength envelope for each specified channel Raises ------ ParameterError if neither ``(y, sr)`` nor ``S`` are provided See Also -------- onset_strength Notes ----- This function caches at level 30. Examples -------- First, load some audio and plot the spectrogram >>> import matplotlib.pyplot as plt >>> y, sr = librosa.load(librosa.ex('choice'), duration=5) >>> D = np.abs(librosa.stft(y)) >>> fig, ax = plt.subplots(nrows=2, sharex=True) >>> img1 = librosa.display.specshow(librosa.amplitude_to_db(D, ref=np.max), ... y_axis='log', x_axis='time', ax=ax[0]) >>> ax[0].set(title='Power spectrogram') >>> ax[0].label_outer() >>> fig.colorbar(img1, ax=[ax[0]], format="%+2.f dB") Construct a standard onset function over four sub-bands >>> onset_subbands = librosa.onset.onset_strength_multi(y=y, sr=sr, ... channels=[0, 32, 64, 96, 128]) >>> img2 = librosa.display.specshow(onset_subbands, x_axis='time', ax=ax[1]) >>> ax[1].set(ylabel='Sub-bands', title='Sub-band onset strength') >>> fig.colorbar(img2, ax=[ax[1]]) Nfmaxg?zlag=z must be a positive integerz max_size=)rrrXrrrM)r"zReference spectrum shape z must match input spectrum .r&TF)rFpadr"rN)rrrr constant)modeg?ggGzrI)rr8r-meanris_positive_intrabsr power_to_db atleast_2dscipyndimagemaximum_filter1dshapemaximumslicecallablesyncr5r[signallfilter)rrr?rXrr@rArBrCrDrErFrHr onset_envr[ pad_width_paddings r=rrsUt &#(+GG    $tC5(CDEE    )y 2MNOO y FF7TQ2UzTVT U   Q  == aA  { q=C--00H20FC agg ' {2MaggY W  #st) s3#:.I 3 *I C$K= II x9#B I Uq:~.. (/!vG/y>1%GBKy' ;ILL((#tsElITV(W c=QWWR[=01 0s2 H()__doc__numpyr-rc_cacherrrutil.exceptionsrfeature.spectralrtypingr r r r r r__all__ndarrayfloatr5r7strrrrrhrrIr>r=r|s  +,EE W #+/#'x x xRZZ( x  x  x RZZ x xx xxZZxz#" $"&15V V V  V V  V "** VV Vh Vhn-.VVZZVrHBJJH HrzzHVR#" $"&15@DD D D  D  D  D DD "** DD Dh Dhn-.DuXc]HUO;<=DD ZZ!DDr>