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 inspectingfluid.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 filterFluidDataSet
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 afluid.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 afluid.dataset
into a specified number of clusters. - fluid.knnclassifier The
fluid.knnclassifier
object implements a K-Nearest Neighbors classifier, leveraging afluid.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 withfluid.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 afluid.labelset
from afluid.dataset
into a text object. - fluid.mds The
fluid.mds
object performs Multidimensional Scaling (MDS) for dimensionality reduction on afluid.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 byfluid.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 afluid.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 withfluid.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 afluid.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 tofluid.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 byfluid.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 aFluidDataSet
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 afluid.dataset
. - fluid.waveform The
fluid.waveform
object visualizes multichannel audio waveforms, feature data, slices, and spectrograms within Pure Data.