o Si]@sFddlmZddlZddlmZddlmZmZm Z GdddZ dS))OptionalN)FeatureExtractor)DecibelsSecondscompute_num_framesc @seZdZdZ  ddedejdedede ef d d Z e d d Z e d ejfddZ e d ejfddZded ejfddZ  ddejdede edefddZdS) FeatureMixera^ Utility class to mix multiple feature matrices into a single one. It should be instantiated separately for each mixing session (i.e. each ``MixedCut`` will create a separate ``FeatureMixer`` to mix its tracks). It is initialized with a numpy array of features (typically float32) that represents the "reference" signal for the mix. Other signals can be mixed to it with different time offsets and SNRs using the ``add_to_mix`` method. The time offset is relative to the start of the reference signal (only positive values are supported). The SNR is relative to the energy of the signal used to initialize the ``FeatureMixer``. It relies on the ``FeatureExtractor`` to have defined ``mix`` and ``compute_energy`` methods, so that the ``FeatureMixer`` knows how to scale and add two feature matrices together. @Nfeature_extractor base_feats frame_shift padding_valuereference_energycCsj||_|g|_|jdkrdn|jd|_g|_||_||_|jdj|_|dur0| ||_ dS||_ dS)ah FeatureMixer's constructor. :param feature_extractor: The ``FeatureExtractor`` instance that specifies how to mix the features. :param base_feats: The features used to initialize the ``FeatureMixer`` are a point of reference in terms of energy and offset for all features mixed into them. :param frame_shift: Required to correctly compute offset and padding during the mix. :param padding_value: The value used to pad the shorter features during the mix. This value is adequate only for log space features. For non-log space features, e.g. energies, use either 0 or a small positive value like 1e-5. :param reference_energy: Optionally pass a reference energy value to compute SNRs against. This might be required when ``base_feats`` correspond to padding energies. rN) r tracksndimshape num_channelsgainsr r dtypecompute_energyr )selfr r r r r rI/home/ubuntu/.local/lib/python3.10/site-packages/lhotse/features/mixer.py__init__s zFeatureMixer.__init__cCs|jdjdS)Nrr)rrrrrr num_features>szFeatureMixer.num_featuresreturncCs t|jS)z Return a numpy ndarray with the shape (num_tracks, num_frames, num_features), where each track's feature matrix is padded and scaled adequately to the offsets and SNR used in ``add_to_mix`` call. )npstackrrrrr unmixed_featsBs zFeatureMixer.unmixed_featscCs@|jd}t|jdd|jD] \}}|jj|||d}q|S)z Return a numpy ndarray with the shape (num_frames, num_features) - a mono mixed feature matrix of the tracks supplied with ``add_to_mix`` calls. rrN) features_a features_benergy_scaling_factor_b)rziprr mix)rresult feats_to_addgainrrr mixed_featsJs zFeatureMixer.mixed_feats num_framescCs2tj|jdkr ||jfn||j|jf|j|jdS)Nr)r fill_valuer)rfullrrr r)rr+rrr_get_dummy_arrayWs  zFeatureMixer._get_dummy_arrayfeats sampling_ratesnroffsetcCs\t|dkrdS|dksJd|jdj|jksJd|jd}t||j|d}|jd}|jd|}t||} |} || kr_tt|jD]} t |j| | | |g} | |j| <qH|dkrmt | || g} || kr}t | | | |g} d} |dur|j dkr|j |}|dkr|j d| d }||} |j| |j| dS) a Add feature matrix of a new track into the mix. :param feats: A 2D feature matrix to be mixed in. :param sampling_rate: The sampling rate of ``feats`` :param snr: Signal-to-noise ratio, assuming ``feats`` represents noise (positive SNR - lower ``feats`` energy, negative SNR - higher ``feats`` energy) :param offset: How many seconds to shift ``feats`` in time. For mixing, the signal will be padded before the start with low energy values. rNr/z+Negative offset in mixing is not supported.z%Feature dimensions mismatch in mixing)durationr r1g?g$@ )lenrrrr rmaxrangervstackr.r r rappendr)rr0r1r2r3reference_featsnum_frames_offsetcurrent_num_framesincoming_num_framesmix_num_framesr(idx padded_trackr)added_feats_energy target_energyrrr add_to_mixdsT          zFeatureMixer.add_to_mix)rN)Nr/)__name__ __module__ __qualname____doc__rrndarrayrfloatrrpropertyrr!r*intr.rrDrrrrr sB $  r) typingrnumpyrlhotse.features.baser lhotse.utilsrrrrrrrrs