Package com.tagtraum.audiokern.audioprocessor

Classes that implement the SignalPullProcessor or SignalProcessor interface. To be used in digital signal processing, e.g. audio fingerprint calculation, key calculation, etc. Some if these classes are experimental. YMMV.

Interface Summary

Interface	Description
AbstractFluxProcessor.FluxCalculator<T extends AudioBuffer>
RoughnessProcessor.Roughness
SpectralCentroidProcessor.WeightFunction	Weight function to be used when computing the weighted sum of all powers.

Class Summary

Class	Description
AbstractFluxProcessor<T extends AudioBuffer>	Computes the flux between two AudioBuffers.
AbstractFluxProcessor.AbstractFluxCalculator<T extends AudioBuffer>
AudioSpectrumFunctions	AudioSpectrumFunctions.
AudioSpectrumFunctions.AudioSpectrumAveraging	Effectively combining every three bins in a row into a single bins containing the weighted average.
AudioSpectrumFunctions.LinearBackgroundRemoval	Implements a noise reduction/whitening scheme for linear-frequency spectra.
AudioSpectrumFunctions.LogFrequencyBackgroundRemoval	Implements a noise reduction/whitening scheme for log-frequency spectra with an integer number of bins per semitone similar to the pre-processing defined in "Approximate note transcription for the improved identification of difficult chords" by M.
AudioSpectrumFunctions.LogFrequencySpectrumToPitchAveraging	Effectively down-samples the bin resolution of a LogFrequencySpectrum to one bin per semitone by calculating a weighted average.
AudioSpectrumFunctions.LogFrequencySpectrumToPitchDownsampling	Effectively down-samples the bin resolution of a LogFrequencySpectrum to one bin per semitone by picking one of multiple bins and discarding the others.
BidirectionalFilterProcessor	Bidirectional Filter Processor.
FloatCollector	Collects Floats in a float array.
FluxProcessor	Calculates the flux between two consecutive AudioBuffer's data.
HarteConcertPitch	Adjusts spectra so that they are in "concert pitch", i.e.
HighLevelFeaturePipelines	HighLevelFeaturePipelines.
LinearFrequencyConcertPitch	Adjusts spectra so that they are in "concert pitch", i.e.
ListCollector<E>	Collects objects in a list. In push mode, downstream processors are handed the list when ListCollector.flush() is called.
LogFrequencyConcertPitch	Adjusts spectra so that they are in "concert pitch", i.e.
Max1NormMean<T extends AudioSpectrum>	Max1Norm mean.
MFCC	MFCC.
PumpProgressAdapter	Allows progress tracking of SignalPump.pump().
RoughnessProcessor	Computes the sensory dissonance also known as roughness.
SpectralCentroidProcessor	Computes the frequency of the centroid of a given power spectrum.
SpectralCentroidProcessor.Centroid
SpectralFeaturePipelines	Extracts low level audio features based on frequency domain values.
SpectralFeaturePipelines.MagnitudesSumFunction<T extends AudioBuffer>	Aggregate function that joins multiple buffers by adding up their magnitudes, index by index.
SpectralFluxProcessor<T extends AudioBuffer>	Computes the spectral flux between two LinearFrequencySpectrum.
TemporalFeaturePipelines	Extracts low level audio features based on time domain values.