}Kg~3fdZddlZddlZddlZddlmZddlm Z ddlm Z ddl m Z ddl mZdd lmZmZdd lmZdd lmZmZmZmZdd lmZmZgd Zdddddej:dededededej:f dZ ddddddddddejBd dej:dededeedeed ed!e"d"eded#ed$eed%ededej:fd&Z#d'dd(d)dd*d+ej:d,ed-ed.ee$d/ed0edej:fd1Z%d'dd(d)dd*d+ej:d,ed-ed.ee$d/ed0ededej:fd2Z&y)3zFeature inversionN)ParameterError) griffinlim) db_to_power)tiny)filters)nnls expand_to) DTypeLike)AnyCallableOptionalUnion) _WindowSpec _PadModeSTFT) mel_to_stft mel_to_audio mfcc_to_mel mfcc_to_audioi"Vig@srn_fftpowerMrrrkwargsreturnc tjd|||jd|jd|}t ||}t j |d|z |S)a Approximate STFT magnitude from a Mel power spectrogram. Parameters ---------- M : np.ndarray [shape=(..., n_mels, n), non-negative] The spectrogram as produced by `feature.melspectrogram` sr : number > 0 [scalar] sampling rate of the underlying signal n_fft : int > 0 [scalar] number of FFT components in the resulting STFT power : float > 0 [scalar] Exponent for the magnitude melspectrogram **kwargs : additional keyword arguments for Mel filter bank parameters fmin : float >= 0 [scalar] lowest frequency (in Hz) fmax : float >= 0 [scalar] highest frequency (in Hz). If `None`, use ``fmax = sr / 2.0`` htk : bool [scalar] use HTK formula instead of Slaney norm : {None, 'slaney', or number} [scalar] If 'slaney', divide the triangular mel weights by the width of the mel band (area normalization). If numeric, use `librosa.util.normalize` to normalize each filter by to unit l_p norm. See `librosa.util.normalize` for a full description of supported norm values (including `+-np.inf`). Otherwise, leave all the triangles aiming for a peak value of 1.0 dtype : np.dtype The data type of the output basis. By default, uses 32-bit (single-precision) floating point. Returns ------- S : np.ndarray [shape=(..., n_fft, t), non-negative] An approximate linear magnitude spectrogram See Also -------- librosa.feature.melspectrogram librosa.stft librosa.filters.mel librosa.util.nnls Examples -------- >>> y, sr = librosa.load(librosa.ex('trumpet')) >>> S = librosa.util.abs2(librosa.stft(y)) >>> mel_spec = librosa.feature.melspectrogram(S=S, sr=sr) >>> S_inv = librosa.feature.inverse.mel_to_stft(mel_spec, sr=sr) Compare the results visually >>> import matplotlib.pyplot as plt >>> fig, ax = plt.subplots(nrows=3, sharex=True, sharey=True) >>> img = librosa.display.specshow(librosa.amplitude_to_db(S, ref=np.max, top_db=None), ... y_axis='log', x_axis='time', ax=ax[0]) >>> ax[0].set(title='Original STFT') >>> ax[0].label_outer() >>> librosa.display.specshow(librosa.amplitude_to_db(S_inv, ref=np.max, top_db=None), ... y_axis='log', x_axis='time', ax=ax[1]) >>> ax[1].set(title='Reconstructed STFT') >>> ax[1].label_outer() >>> librosa.display.specshow(librosa.amplitude_to_db(np.abs(S_inv - S), ... ref=S.max(), top_db=None), ... vmax=0, y_axis='log', x_axis='time', cmap='magma', ax=ax[2]) >>> ax[2].set(title='Residual error (dB)') >>> fig.colorbar(img, ax=ax, format="%+2.f dB") )rrn_melsdtype?)out)rmelshaper r npr)rrrrr mel_basisinverses [/home/alanp/www/video.onchill/myenv/lib/python3.12/site-packages/librosa/feature/inverse.pyrrsZZ  U1772;aggAGI9a G 88GS5[g 66hannTconstant ) rr hop_length win_lengthwindowcenterpad_modern_iterlengthr r.r/r0r1r2r3r4r c Lt|f|||d| } t| | |||||| | | S)a& Invert a mel power spectrogram to audio using Griffin-Lim. This is primarily a convenience wrapper for: >>> S = librosa.feature.inverse.mel_to_stft(M) >>> y = librosa.griffinlim(S) Parameters ---------- M : np.ndarray [shape=(..., n_mels, n), non-negative] The spectrogram as produced by `feature.melspectrogram` sr : number > 0 [scalar] sampling rate of the underlying signal n_fft : int > 0 [scalar] number of FFT components in the resulting STFT hop_length : None or int > 0 The hop length of the STFT. If not provided, it will default to ``n_fft // 4`` win_length : None or int > 0 The window length of the STFT. By default, it will equal ``n_fft`` window : string, tuple, number, function, or np.ndarray [shape=(n_fft,)] A window specification as supported by `stft` or `istft` center : boolean If `True`, the STFT is assumed to use centered frames. If `False`, the STFT is assumed to use left-aligned frames. pad_mode : string If ``center=True``, the padding mode to use at the edges of the signal. By default, STFT uses zero padding. power : float > 0 [scalar] Exponent for the magnitude melspectrogram n_iter : int > 0 The number of iterations for Griffin-Lim length : None or int > 0 If provided, the output ``y`` is zero-padded or clipped to exactly ``length`` samples. dtype : np.dtype Real numeric type for the time-domain signal. Default is 32-bit float. **kwargs : additional keyword arguments for Mel filter bank parameters fmin : float >= 0 [scalar] lowest frequency (in Hz) fmax : float >= 0 [scalar] highest frequency (in Hz). If `None`, use ``fmax = sr / 2.0`` htk : bool [scalar] use HTK formula instead of Slaney norm : {None, 'slaney', or number} [scalar] If 'slaney', divide the triangular mel weights by the width of the mel band (area normalization). If numeric, use `librosa.util.normalize` to normalize each filter by to unit l_p norm. See `librosa.util.normalize` for a full description of supported norm values (including `+-np.inf`). Otherwise, leave all the triangles aiming for a peak value of 1.0 Returns ------- y : np.ndarray [shape(..., n,)] time-domain signal reconstructed from ``M`` See Also -------- librosa.griffinlim librosa.feature.melspectrogram librosa.filters.mel librosa.feature.inverse.mel_to_stft r) r3r.r/rr0r1r r4r2)rr)rrrr.r/r0r1r2rr3r4r rstfts r)rrnsH` q DRuE DV DD    r*orthor!rdct_typenormrefliftermfccrr:r;r<r=c|dkDr|jd}tjdd|z|j}t ||j d}d|dztj tj|z|z zz}tjtj|tj|jjkrtjdtd ||t|zz }n|dk7r t!d t"j$j'|d||| } t)| | } | S) a[Invert Mel-frequency cepstral coefficients to approximate a Mel power spectrogram. This inversion proceeds in two steps: 1. The inverse DCT is applied to the MFCCs 2. `librosa.db_to_power` is applied to map the dB-scaled result to a power spectrogram Parameters ---------- mfcc : np.ndarray [shape=(..., n_mfcc, n)] The Mel-frequency cepstral coefficients n_mels : int > 0 The number of Mel frequencies dct_type : {1, 2, 3} Discrete cosine transform (DCT) type By default, DCT type-2 is used. norm : None or 'ortho' If ``dct_type`` is `2 or 3`, setting ``norm='ortho'`` uses an orthonormal DCT basis. Normalization is not supported for `dct_type=1`. ref : float Reference power for (inverse) decibel calculation lifter : number >= 0 If ``lifter>0``, apply inverse liftering (inverse cepstral filtering):: M[n, :] <- M[n, :] / (1 + sin(pi * (n + 1) / lifter) * lifter / 2) Returns ------- M : np.ndarray [shape=(..., n_mels, n)] An approximate Mel power spectrum recovered from ``mfcc`` Warns ----- UserWarning due to critical values in lifter array that invokes underflow. See Also -------- librosa.feature.mfcc librosa.feature.melspectrogram scipy.fftpack.dct rr)r )ndimaxesg?z@lifter array includes critical values that may invoke underflow.r)messagecategory stacklevelz1MFCC to mel lifter must be a non-negative number.)axistyper;n)r<)r%r&aranger r rAsinpianyabsfinfoepswarningswarn UserWarningrrscipyfftpackidctr) r>rr:r;r<r=n_mfccidx lifter_sinelogmelmelspecs r)rrs hzBii1v:TZZ8$))"5&3, f0D)EEE  66"&&%1B1B(C(G(GG H MMZ$ {T$Z/0 1PQQ ]]  2H46  RF%f#6G Nr*c <t||||||}t|fi|S)a Convert Mel-frequency cepstral coefficients to a time-domain audio signal This function is primarily a convenience wrapper for the following steps: 1. Convert mfcc to Mel power spectrum (`mfcc_to_mel`) 2. Convert Mel power spectrum to time-domain audio (`mel_to_audio`) Parameters ---------- mfcc : np.ndarray [shape=(..., n_mfcc, n)] The Mel-frequency cepstral coefficients n_mels : int > 0 The number of Mel frequencies dct_type : {1, 2, 3} Discrete cosine transform (DCT) type By default, DCT type-2 is used. norm : None or 'ortho' If ``dct_type`` is `2 or 3`, setting ``norm='ortho'`` uses an orthonormal DCT basis. Normalization is not supported for ``dct_type=1``. ref : float Reference power for (inverse) decibel calculation lifter : number >= 0 If ``lifter>0``, apply inverse liftering (inverse cepstral filtering):: M[n, :] <- M[n, :] / (1 + sin(pi * (n + 1) / lifter)) * lifter / 2 **kwargs : additional keyword arguments to pass through to `mel_to_audio` M : np.ndarray [shape=(..., n_mels, n), non-negative] The spectrogram as produced by `feature.melspectrogram` sr : number > 0 [scalar] sampling rate of the underlying signal n_fft : int > 0 [scalar] number of FFT components in the resulting STFT hop_length : None or int > 0 The hop length of the STFT. If not provided, it will default to ``n_fft // 4`` win_length : None or int > 0 The window length of the STFT. By default, it will equal ``n_fft`` window : string, tuple, number, function, or np.ndarray [shape=(n_fft,)] A window specification as supported by `stft` or `istft` center : boolean If `True`, the STFT is assumed to use centered frames. If `False`, the STFT is assumed to use left-aligned frames. pad_mode : string If ``center=True``, the padding mode to use at the edges of the signal. By default, STFT uses zero padding. power : float > 0 [scalar] Exponent for the magnitude melspectrogram n_iter : int > 0 The number of iterations for Griffin-Lim length : None or int > 0 If provided, the output ``y`` is zero-padded or clipped to exactly ``length`` samples. dtype : np.dtype Real numeric type for the time-domain signal. Default is 32-bit float. **kwargs : additional keyword arguments for Mel filter bank parameters fmin : float >= 0 [scalar] lowest frequency (in Hz) fmax : float >= 0 [scalar] highest frequency (in Hz). If `None`, use ``fmax = sr / 2.0`` htk : bool [scalar] use HTK formula instead of Slaney Returns ------- y : np.ndarray [shape=(..., n)] A time-domain signal reconstructed from `mfcc` See Also -------- mfcc_to_mel mel_to_audio librosa.feature.mfcc librosa.griffinlim scipy.fftpack.dct r9)rr)r>rr:r;r<r=rmel_specs r)rrs.j VhTs6H  +F ++r*)'__doc__rPnumpyr& scipy.fftpackrSutil.exceptionsr core.spectrumrr util.utilsrrutilr r numpy.typingr typingr r rr_typingrr__all__ndarrayfloatintrfloat32boolrstrrrr#r*r)rosR,&'""11/ I  U7 zzU7 U7  U7  U7  U7ZZU7v $ $ ' zz] zz] ]  ]  ]  ] ] ]] ] ] SM] ]]ZZ]F!J **J J J 3- J  J JZZJ`!Y, **Y, Y, Y, 3- Y,  Y, Y,Y,ZZY,r*