Cargando…

Sample-level sound synthesis with recurrent neural networks and conceptors

Conceptors are a recent development in the field of reservoir computing; they can be used to influence the dynamics of recurrent neural networks (RNNs), enabling generation of arbitrary patterns based on training data. Conceptors allow interpolation and extrapolation between patterns, and also provi...

Descripción completa

Detalles Bibliográficos
Autor principal: Kiefer, Chris
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924416/
https://www.ncbi.nlm.nih.gov/pubmed/33816858
http://dx.doi.org/10.7717/peerj-cs.205
_version_ 1783659084680003584
author Kiefer, Chris
author_facet Kiefer, Chris
author_sort Kiefer, Chris
collection PubMed
description Conceptors are a recent development in the field of reservoir computing; they can be used to influence the dynamics of recurrent neural networks (RNNs), enabling generation of arbitrary patterns based on training data. Conceptors allow interpolation and extrapolation between patterns, and also provide a system of boolean logic for combining patterns together. Generation and manipulation of arbitrary patterns using conceptors has significant potential as a sound synthesis method for applications in computer music but has yet to be explored. Conceptors are untested with the generation of multi-timbre audio patterns, and little testing has been done on scalability to longer patterns required for audio. A novel method of sound synthesis based on conceptors is introduced. Conceptular Synthesis is based on granular synthesis; sets of conceptors are trained to recall varying patterns from a single RNN, then a runtime mechanism switches between them, generating short patterns which are recombined into a longer sound. The quality of sound resynthesis using this technique is experimentally evaluated. Conceptor models are shown to resynthesise audio with a comparable quality to a close equivalent technique using echo state networks with stored patterns and output feedback. Conceptor models are also shown to excel in their malleability and potential for creative sound manipulation, in comparison to echo state network models which tend to fail when the same manipulations are applied. Examples are given demonstrating creative sonic possibilities, by exploiting conceptor pattern morphing, boolean conceptor logic and manipulation of RNN dynamics. Limitations of conceptor models are revealed with regards to reproduction quality, and pragmatic limitations are also shown, where rises in computation and memory requirements preclude the use of these models for training with longer sound samples. The techniques presented here represent an initial exploration of the sound synthesis potential of conceptors, demonstrating possible creative applications in sound design; future possibilities and research questions are outlined.
format Online
Article
Text
id pubmed-7924416
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-79244162021-04-02 Sample-level sound synthesis with recurrent neural networks and conceptors Kiefer, Chris PeerJ Comput Sci Artificial Intelligence Conceptors are a recent development in the field of reservoir computing; they can be used to influence the dynamics of recurrent neural networks (RNNs), enabling generation of arbitrary patterns based on training data. Conceptors allow interpolation and extrapolation between patterns, and also provide a system of boolean logic for combining patterns together. Generation and manipulation of arbitrary patterns using conceptors has significant potential as a sound synthesis method for applications in computer music but has yet to be explored. Conceptors are untested with the generation of multi-timbre audio patterns, and little testing has been done on scalability to longer patterns required for audio. A novel method of sound synthesis based on conceptors is introduced. Conceptular Synthesis is based on granular synthesis; sets of conceptors are trained to recall varying patterns from a single RNN, then a runtime mechanism switches between them, generating short patterns which are recombined into a longer sound. The quality of sound resynthesis using this technique is experimentally evaluated. Conceptor models are shown to resynthesise audio with a comparable quality to a close equivalent technique using echo state networks with stored patterns and output feedback. Conceptor models are also shown to excel in their malleability and potential for creative sound manipulation, in comparison to echo state network models which tend to fail when the same manipulations are applied. Examples are given demonstrating creative sonic possibilities, by exploiting conceptor pattern morphing, boolean conceptor logic and manipulation of RNN dynamics. Limitations of conceptor models are revealed with regards to reproduction quality, and pragmatic limitations are also shown, where rises in computation and memory requirements preclude the use of these models for training with longer sound samples. The techniques presented here represent an initial exploration of the sound synthesis potential of conceptors, demonstrating possible creative applications in sound design; future possibilities and research questions are outlined. PeerJ Inc. 2019-07-08 /pmc/articles/PMC7924416/ /pubmed/33816858 http://dx.doi.org/10.7717/peerj-cs.205 Text en ©2019 Kiefer http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Artificial Intelligence
Kiefer, Chris
Sample-level sound synthesis with recurrent neural networks and conceptors
title Sample-level sound synthesis with recurrent neural networks and conceptors
title_full Sample-level sound synthesis with recurrent neural networks and conceptors
title_fullStr Sample-level sound synthesis with recurrent neural networks and conceptors
title_full_unstemmed Sample-level sound synthesis with recurrent neural networks and conceptors
title_short Sample-level sound synthesis with recurrent neural networks and conceptors
title_sort sample-level sound synthesis with recurrent neural networks and conceptors
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7924416/
https://www.ncbi.nlm.nih.gov/pubmed/33816858
http://dx.doi.org/10.7717/peerj-cs.205
work_keys_str_mv AT kieferchris samplelevelsoundsynthesiswithrecurrentneuralnetworksandconceptors