Acoustic features

The module features is an ensemble of functions to characterize audio signals using temporal and spectral features, and ecoacoustic indices.

Spectro-temporal features

`shape_features`(Sxx[, resolution, rois])	Computes time-frequency shape coefficients at multiple resolutions using 2D Gabor filters.
`shape_features_raw`(im[, resolution, opt_shape])	Computes raw shape of 2D signal (image or spectrogram) at multiple resolutions using 2D Gabor filters.
`opt_shape_presets`(resolution[, opt_shape])	Set parameters for multiresolution analysis using presets or custom parameters.
`filter_multires`(Sxx, kernels[, npyr, rescale])	Computes 2D wavelet coefficients at multiple scales using Gaussian pyramid transformation to downscale the input spectrogram.
`filter_bank_2d_nodc`(frequency, ntheta[, ...])	Build an ensemble of complex 2D Gabor filters with no DC offset.
`centroid_features`(Sxx[, rois, im_rois])	Computes intensity centroid of a spectrogram.
`all_shape_features`(s, fs, rois[, ...])	Computes shape and central frequency features from signal at specified time-frequency limits defined by regions of interest (ROIs).

Alpha acoustic indices

`temporal_median`(s[, mode, Nt])	Computes the median of the envelope of an audio signal.
`temporal_entropy`(s[, compatibility, mode, Nt])	Computes the entropy of the envelope of an audio signal.
`acoustic_richness_index`(Ht_array, M_array)	Compute the acoustic richness index of an audio file.
`temporal_activity`(s[, dB_threshold, mode, Nt])	Compute the acoustic activity index in temporal domain.
`temporal_events`(s, fs[, dB_threshold, ...])	Compute the acoustic event index from an audio signal [R6d576de36602-1] [R6d576de36602-2].
`acoustic_complexity_index`(Sxx)	Compute the Acoustic Complexity Index (ACI) from a spectrogram [R669a90ddf753-1].
`frequency_entropy`(X[, compatibility])	Computes the spectral entropy of a power spectral density (1d) or power spectrogram density (2d).
`number_of_peaks`(X, fn[, mode, min_peak_val, ...])	Count the number of frequency peaks on a mean spectrum.
`spectral_entropy`(Sxx, fn[, flim, display])	Compute different entropies based on the average spectrum, its variance, and its maxima [R1479941c7526-1] [R1479941c7526-2]
`spectral_activity`(Sxx_dB[, dB_threshold])	Compute the acoustic activity on a spectrogram.
`spectral_events`(Sxx_dB, dt[, dB_threshold, ...])	Compute acoustic events from a spectrogram [Rf0ffa84335f9-1] [Rf0ffa84335f9-2].
`spectral_cover`(Sxx, fn[, dB_threshold, ...])	Compute the proportion (cover) of the spectrogram above a threshold for three bandwidths : low frequency band (LF), medium frequency band (MF) and high frequency band (HF) [R1ef1ced9d4c7-1] [R1ef1ced9d4c7-2].
`soundscape_index`(Sxx_power, fn[, ...])	Compute the Normalized Difference Soundscape Index from a power spectrogram [Re8a3e6a1d49a-1].
`bioacoustics_index`(Sxx, fn[, flim, R_compatible])	Compute the Bioacoustics Index from a spectrogram [R4387573841e2-1].
`acoustic_diversity_index`(Sxx, fn[, fmin, ...])	Compute the Acoustic Diversity Index (ADI) from a spectrogram [R544b09b311be-1].
`acoustic_eveness_index`(Sxx, fn[, fmin, ...])	Compute the Acoustic Eveness Index (AEI) from a spectrogram [Re3dd41c8e02e-1].
`roughness`(x[, norm, axis])	Computes the roughness (depends on the number of peaks and their amplitude) of a vector or matrix x (i.e. waveform, spectrogram...) Roughness = sum(second_derivation(x)²) [Rc5776a89b74b-1] [Rc5776a89b74b-2].
`temporal_leq`(s, fs, gain[, Vadc, ...])	Computes the Equivalent Continuous Sound level (Leq) of an audio signal in the time domain.
`spectral_leq`(X, gain[, Vadc, sensitivity, ...])	Computes the Equivalent Continuous Sound level (Leq) from a power spectrum (1d) or power spectrogram (2d).
`surface_roughness`(x[, norm])	Compute the surface roughness index of a signal (1D) or a spectrogram (2D).
`tfsd`(Sxx, fn, tn[, flim, log, mode, display])	Compute the Time frequency derivation index (tfsd) from a spectrogram.
`more_entropy`(x[, order, axis])	Compute the entropy of an audio signal using multiple methods.
`acoustic_gradient_index`(Sxx, dt[, order, ...])	Compute the Acoustic Gradient Index (AGI) from a raw spectrogram.
`frequency_raoq`(S_power, fn[, bin_step])	Compute Rao's quadratic entropy on a power spectrum (1d).
`region_of_interest_index`(Sxx_dB_noNoise, tn, fn)	Compute an acoustic activity index based on the regions of interested detected on a spectrogram.
`all_temporal_alpha_indices`(s, fs[, verbose, ...])	Compute 16 temporal domain acoustic indices.
`all_spectral_alpha_indices`(Sxx_power, tn, fn)	Computes the acoustic indices in spectral (spectrum (1d) or spectrogram (2d)) domain.

Temporal features

`temporal_moments`(s[, fs, roi])	Computes the first 4th moments of an audio signal, mean, variance, skewness, kurtosis.
`zero_crossing_rate`(s, fs[, roi])	Compute the zero crossing rate feature of an audio signal.
`temporal_duration`(s, fs[, nperseg, roi, ...])	Compute the temporal duration of the waveform.
`temporal_quantile`(s, fs[, q, nperseg, roi, ...])	Compute the q-th temporal quantile of the waveform or spectrum.
`all_temporal_features`(s, fs[, nperseg, roi, ...])	Compute all the temporal features for a signal.

Spectral features

`spectral_moments`(X[, axis])	Computes the first 4th moments of an amplitude spectrum (1d) or spectrogram (2d), mean, variance, skewness, kurtosis.
`peak_frequency`(s, fs[, method, nperseg, ...])	Compute the peak frequency for audio signal.
`spectral_quantile`(s, fs[, q, nperseg, roi, ...])	Compute the q-th quantile of the power spectrum.
`spectral_bandwidth`(s, fs[, nperseg, roi, ...])	Compute the bandwith of the power spectrum.
`all_spectral_features`(s, fs[, nperseg, roi, ...])	Compute all the spectral features for a signal.

Composite acoustic features

`graphical_soundscape`(data, threshold_abs[, ...])	Computes a graphical soundscape from a given DataFrame of audio files.
`plot_graph`(graph[, ax, savefig, fname])	Plots a graphical soundscape