5.6 KiB
Concatenative synthesis
101
Concatenative synthesis is a technique for synthesising sounds by concatenating short samples of recorded sound (called units).
synonyms for concatenation
102
- types
- audio mosaicing
Audio and databases
- samplers and smart samplers
- GAN incubation.ai.audio
- for GAN vs. diffusion see: https://cyberneticforests.substack.com/p/what-was-the-gan
- incubation.audio.sample.managment
- See also: incubation.concepts.DatabaseArt
- audio source separation
- https://danmackinlay.name/notebook/source_separation.html
- non-matrix factorization aka nmf
Tools
Paid
- FactorSynth - https://anemond.net/
- ReformerPro - https://www.krotosaudio.com/products/
Promising
- https://colab.research.google.com/github/stevetjoa/musicinformationretrieval.com/blob/gh-pages/nmf_audio_mosaic.ipynb
- https://soundlab.cs.princeton.edu/research/mosievius/
- http://imtr.ircam.fr/imtr/Corpus_Based_Synthesis
- https://github.com/benhackbarth/audioguide
- OSX but promising
- https://rodrigoconstanzo.com/combine/
- also M4L or runtime
- https://neutone.space/
- probably more DigitalGardenAnabasis/ai.music
Audiostellar [8/10]
- https://audiostellar.xyz/
- https://www.arj.no/tag/sox/
- cataRT
- ableton link incoming
- https://www.arj.no/tag/sox/
timbreIDLib Pure Data
https://github.com/wbrent/timbreIDLib
timbreIDLib is a library of audio analysis externals for Pure Data. The classification external [timbreID] accepts arbitrary lists of audio features and attempts to find the best match between an input feature and previously stored training instances. The library can be used for a variety of real-time and non-real-time applications, including sound classification, sound searching, sound visualization, automatic segmenting, ordering of sounds by timbre, key and tempo estimation, and concatenative synthesis.
flucoma
TheFluidCorpusManipulationproject(FluCoMa)instigatesnewmusicalwaysofexploitingever-growingbanksofsoundandgestureswithinthedigitalcompositionprocess,bybringingbreakthroughsofsignaldecompositionDSPandmachinelearningtothetoolsetoftechno-fluentcomputercomposers,creativecodersanddigitalartists.
- PD / Max / supercollider also
- reaper also reacoma
samplebrain [4/10]
https://gitlab.com/then-try-this/samplebrain
cataRT
- https://ircam-ismm.github.io/max-msp/catart.html#videos
- it is backed by https://ircam-ismm.github.io/max-msp/mubu.html
AudioGuide
- mac os / offline / to reaper export
- https://github.com/benhackbarth/audioguide
rhytmcat
Unsorted
-
https://en.wikipedia.org/wiki/Festival_Speech_Synthesis_System
-
https://en.wikipedia.org/wiki/Sinsy
-
Sinsy (Singing Voice Synthesis System) (しぃんしぃ) is an online Hidden Markov model (HMM)-based singing voice synthesis system by the Nagoya Institute of Technology that was created under the Modified BSD license.
- http://www.sinsy.jp/
-
-
https://www.audiolabs-erlangen.de/resources/MIR/2015-ISMIR-LetItBee
Also there were mogees - https://www.youtube.com/watch?v=G_hBhORGE6Y
-
python concatenative
AudioFlux
- https://libaudioflux.github.io/audioFlux/
audioFluxis a deep learning tool library for audio and music analysis, feature extraction. It supports dozens of time-frequency analysis transformation methods and hundreds of corresponding time-domain and frequency-domain feature combinations. It can be provided to deep learning networks for training, and is used to study various tasks in the audio field such as Classification, Separation, Music Information Retrieval(MIR) and ASR etc.- audio.ai
Articles
- https://direct.mit.edu/comj/article/41/2/21/94580/Rhythmic-Concatenative-Synthesis-for-Electronic
- https://danmackinlay.name/notebook/concatenative_synthesis.html