Skip to content

flucoma

The Fluid Corpus Manipulation project (FluCoMa) instigates new musical ways of exploiting ever-growing banks of sounds and gestures within the digital composition process, by bringing breakthroughs in signal decomposition, DSP, and machine learning to the toolset of techno-fluent computer composers, creative coders, and digital artists.

Contributors

People who contribute to this project.

Objects

  • fluid.ampfeature~ The fluid.ampfeature~ object calculates various amplitude differential features from an audio signal.
  • fluid.ampgate~ fluid.ampgate~ is a real-time absolute amplitude threshold gate detector for audio signals.
  • fluid.ampslice~ The fluid.ampslice~ object performs amplitude-based segmentation of audio signals.
  • fluid.audiotransport~ The fluid.audiotransport~ object performs spectral interpolation between two loaded audio sounds.
  • fluid.bufampfeature The fluid.bufampfeature object calculates an amplitude differential feature from an audio buffer, useful for tasks like event detection or slicing.
  • fluid.bufampgate The fluid.bufampgate object acts as an absolute amplitude threshold gate detector for audio input.
  • fluid.bufampslice fluid.bufampslice is an amplitude-based audio slicer for buffered audio.
  • fluid.bufaudiotransport fluid.bufaudiotransport analyzes two source audio buffers using FFT to derive spectral characteristics.
  • fluid.bufchroma The fluid.bufchroma object computes a histogram of the energy contained within audio signals, specifically focusing on chroma features.
  • fluid.bufcompose The fluid.bufcompose object copies and combines audio data from a source buffer/array to a destination buffer/array, applying a specified gain.
  • fluid.bufflatten The fluid.bufflatten object flattens a multi-channel buffer into a single-channel buffer.
  • fluid.bufhpss The fluid.bufhpss object performs Harmonic-Percussive Source Separation (HPSS) on audio stored in buffers.
  • fluid.bufinfo The fluid.bufinfo object is a utility for inspecting fluid.multiarray objects and other arrays/buffers.
  • fluid.bufloudness The fluid.bufloudness object computes two loudness descriptors: true peak and a loudness measurement that applies broadcasting standard filters to emulate perceived amplitude.
  • fluid.bufmelbands fluid.bufmelbands computes the magnitudes for a specified number of perceptually-evenly spaced mel bands from an audio buffer.
  • fluid.bufmfcc The fluid.bufmfcc object calculates Mel-Frequency Cepstral Coefficients (MFCCs), a classic timbral spectral descriptor.
  • fluid.bufnmf The fluid.bufnmf object performs Non-Negative Matrix Factorisation (NMF) to decompose the spectrum of a sound into multiple components, represented by 'bases' (spectral profiles) and 'activations' (temporal envelopes).
  • fluid.bufnmfcross fluid.bufnmfcross reconstructs a target sound by using components learned from a source sound through Non-negative Matrix Factorization (NMF).
  • fluid.bufnmfseed The fluid.bufnmfseed object computes initial bases and activations for Non-negative Matrix Factorization (NMF) from an input audio buffer.
  • fluid.bufnoveltyfeature The fluid.bufnoveltyfeature object calculates a novelty curve from audio data stored in a buffer.
  • fluid.bufnoveltyslice The fluid.bufnoveltyslice object is a non-realtime audio slicer that identifies segmentation points in a source buffer (srcBuf) by assessing signal novelty.
  • fluid.bufonsetfeature The fluid.bufonsetfeature object calculates various spectral difference features and metrics from an audio buffer, such as Energy, HFC, and SpectralFlux.
  • fluid.bufonsetslice fluid.bufonsetslice implements various spectrum-based onset detection algorithms on audio data stored in a buffer.
  • fluid.bufpitch fluid.bufpitch computes three popular pitch descriptors (frequency and confidence) from an audio buffer.
  • fluid.bufscale The fluid.bufscale object scales numerical values within a buffer from a specified input range to an output range.
  • fluid.bufselect The fluid.bufselect~ object copies specific sets of values from a buffer, allowing selection by channels and indices.
  • fluid.bufselectevery The fluid.bufselectevery object extracts specific frames and/or channels from a buffer at regular intervals.
  • fluid.bufsinefeature The fluid.bufsinefeature object performs interpolated sinusoidal peak tracking on the spectrum of audio data stored in a buffer.
  • fluid.bufsines fluid.bufsines performs sinusoidal modeling on audio buffers, decomposing a source buffer into its sinusoidal and residual components.
  • fluid.bufspectralshape The fluid.bufspectralshape object computes seven spectral shape descriptors (centroid, spread, skewness, kurtosis, rolloff, flatness, crest) from an audio source.
  • fluid.bufstats The fluid.bufstats object calculates various statistical descriptors (e.g., mean, standard deviation, skewness, kurtosis, pitch) from segments within an audio buffer.
  • fluid.bufstft The fluid.bufstft object performs forward and inverse Short-Time Fourier Transforms (STFT) on single-channel audio buffers.
  • fluid.bufthreaddemo The fluid.bufthreaddemo object is a demonstration tool from the Fluid Decomposition Toolkit, designed to illustrate multi-threading concepts in Pure Data.
  • fluid.bufthresh The fluid.bufthresh object processes a source buffer by replacing all values below a specified threshold with zero.
  • fluid.buftransients fluid.buftransients performs non-real-time sinusoidal modeling on audio buffers to detect and extract transients.
  • fluid.buftransientslice The fluid.buftransientslice object extracts transient-based slices from audio buffers.
  • fluid.chroma~ The fluid.chroma~ object analyzes an audio input to compute a histogram of energy across different pitch classes.
  • fluid.concataudiofiles The fluid.concataudiofiles object takes a list of paths to audio files, loads them, and concatenates them into a single audio buffer.
  • fluid.dataset The fluid.dataset object acts as a versatile container for associating data points with unique identifiers, crucial for FluCoMa data analysis.
  • fluid.datasetquery The fluid.datasetquery object allows users to query and filter FluidDataSet objects.
  • fluid.ds2text The fluid.ds2text object is a utility for converting datasets into a text format within Pure Data.
  • fluid.gain~ The fluid.gain~ object controls the amplitude of an audio signal.
  • fluid.grid The fluid.grid object maps a set of 2D points from a fluid.dataset into a rectangular grid.
  • fluid.hpss~ The fluid.hpss~ object performs Harmonic-Percussive Source Separation (HPSS) on an audio input, separating it into harmonic and percussive components.
  • fluid.kdtree The fluid.kdtree object implements a K-dimensional tree for efficient nearest-neighbor searches within multi-dimensional datasets.
  • fluid.kmeans The fluid.kmeans object implements the K-means clustering algorithm, used to group data points from a fluid.dataset into a specified number of clusters.
  • fluid.knnclassifier The fluid.knnclassifier object implements a K-Nearest Neighbors classifier, leveraging a fluid.kdtree for efficient data searching.
  • fluid.knnregressor The fluid.knnregressor object performs K-Nearest Neighbours regression, enabling the prediction of outputs by finding the weighted average of neighboring data points within datasets.
  • fluid.labelset The fluid.labelset object is a container that associates string identifiers with corresponding labels, primarily used in conjunction with fluid.dataset~ for machine learning tasks.
  • fluid.loudness~ The fluid.loudness~ object calculates two audio descriptors: loudness and peak.
  • fluid.ls2text fluid.ls2text is a utility object designed to convert a fluid.labelset from a fluid.dataset into a text object.
  • fluid.mds The fluid.mds object performs Multidimensional Scaling (MDS) for dimensionality reduction on a fluid.dataset.
  • fluid.melbands~ The fluid.melbands~ object calculates the magnitudes of audio signals across a specified number of perceptually evenly spread Mel-frequency bands.
  • fluid.mfcc~ The fluid.mfcc~ object calculates Mel-Frequency Cepstral Coefficients (MFCCs) in real-time, serving as a classic timbral audio descriptor.
  • fluid.mlpclassifier The fluid.mlpclassifier object performs classification using a Multi-Layer Perceptron (MLP) neural network.
  • fluid.mlpregressor The fluid.mlpregressor object performs regression using a Multi-Layer Perceptron (MLP) neural network.
  • fluid.multiarray The fluid.multiarray object creates and manages multi-channel arrays, allowing users to store and retrieve lists of values across multiple independent channels.
  • fluid.nmffilter~ The fluid.nmffilter~ object decomposes and resynthesizes an audio signal by filtering it against spectral templates, or "bases," typically generated by fluid.bufnmf~.
  • fluid.nmfmatch~ The fluid.nmfmatch~ object matches an incoming audio signal against a set of spectral templates, typically derived using Non-negative Matrix Factorization (NMF).
  • fluid.nmfmorph~ The fluid.nmfmorph~ object performs cross-synthesis between two audio sources using Nonnegative Matrix Factorization (NMF) and Optimal Transport (OT).
  • fluid.normalize The fluid.normalize object normalizes a fluid.dataset or a single data point.
  • fluid.noveltyfeature~ The fluid.noveltyfeature~ object calculates the novelty feature of audio in real-time, indicating changes in underlying audio characteristics.
  • fluid.noveltyslice~ The fluid.noveltyslice~ object is a real-time audio slicer that detects "novelty" in an incoming signal to determine slicing points.
  • fluid.onsetfeature~ fluid.onsetfeature~ calculates spectral difference features from an audio signal, primarily for use with fluid.onsetslice~.
  • fluid.onsetslice~ The fluid.onsetslice~ object performs spectrum-based onset detection on audio signals.
  • fluid.pca fluid.pca performs Principal Component Analysis (PCA) on a fluid.dataset to reduce dimensionality, such as transforming 13 MFCC values into 2.
  • fluid.pitch~ fluid.pitch~ is a monophonic pitch descriptor that computes both the fundamental frequency and a confidence score from an audio input.
  • fluid.plotter The fluid.plotter object provides a native graphical user interface for plotting and querying two-dimensional datasets.
  • fluid.robustscale The fluid.robustscale object applies robust scaling to fluid.dataset objects.
  • fluid.s2f The fluid.s2f object converts a symbol (text string) that represents a floating-point number into its numerical float equivalent.
  • fluid.sinefeature~ The fluid.sinefeature~ object calculates spectral difference features, primarily used by fluid.onsetslice~.
  • fluid.sines~ The fluid.sines~ object performs sinusoidal modeling on an audio input, attempting to reconstruct the signal as a bank of sinusoids.
  • fluid.skmeans fluid.skmeans implements the K-means clustering algorithm with cosine similarity.
  • fluid.spectralshape~ fluid.spectralshape~ computes seven spectral shape descriptors from an audio signal: centroid, spread, skewness, kurtosis, rolloff, flatness, and crest.
  • fluid.standardize The fluid.standardize object rescales a FluidDataSet by transforming its data to have a mean of 0 and a standard deviation of 1 for each dimension.
  • fluid.stats The fluid.stats object calculates the rolling mean and sample standard deviation for multichannel control inputs over a specified window.
  • fluid.stftpass~ The help patch for fluid.stftpass~ was empty, so its exact functionality cannot be determined.
  • fluid.transientslice~ fluid.transientslice~ is a real-time audio analysis object that extracts slices from an incoming audio stream based on transient detection.
  • fluid.transients~ fluid.transients~ is a real-time audio object that models and separates transients from its input signal.
  • fluid.umap The fluid.umap object performs Uniform Manifold Approximation and Projection (UMAP) for dimensionality reduction on a fluid.dataset.
  • fluid.waveform The fluid.waveform object visualizes multichannel audio waveforms, feature data, slices, and spectrograms within Pure Data.