A gestural control for a nonlinear sound synthesis method

2000 ◽  
Author(s):  
F. Damiani ◽  
J. Manzolli ◽  
P.J. Tatsch ◽  
A. Maia
Keyword(s):  
Synthesis Method ◽  
Sound Synthesis ◽  
Gestural Control

Partial timbre sound synthesis method and instrument

1986 ◽  
Vol 79 (4) ◽  
pp. 1201-1201
Author(s):  
Sydney A. Alonso ◽  
Cameron W. Jones
Keyword(s):  
Synthesis Method ◽  
Sound Synthesis

scholarly journals Sample-level sound synthesis with recurrent neural networks and conceptors

2018 ◽  
Author(s):  
Chris Kiefer
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Frequency Control ◽  
Synthesis Method ◽  
Sound Synthesis ◽  
Boolean Logic ◽  
Training Data ◽  
Reservoir Computing ◽  
Research Questions ◽  
Granular Synthesis

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 and procedural audio but has yet to be explored. Two novel methods of sound synthesis based on conceptors are 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. Conceptillators are trainable, pitch-controlled oscillators for harmonically rich waveforms, commonly used in a variety of sound synthesis applications. Both systems can exploit conceptor pattern morphing, boolean logic and manipulation of RNN dynamics, enabling new creative sonic possibilities. Experiments reveal how RNN runtime parameters can be used for pitch-independent timestretching and for precise frequency control of cyclic waveforms. They show how these techniques can create highly malleable sound synthesis models, trainable using short sound samples. Limitations are revealed with regards to reproduction quality, and pragmatic limitations are also shown, where exponential 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; future possibilities and research questions are outlined, including possibilities in generative sound.

scholarly journals Impact sound synthesis method of complex structures and the experimental verification

2014 ◽  
Vol 63 (22) ◽  
pp. 224303
Author(s):  
Zhang Bing-Rui ◽  
Chen Ke-An ◽  
Ding Shao-Hu
Keyword(s):  
Experimental Verification ◽  
Synthesis Method ◽  
Sound Synthesis ◽  
Complex Structures

scholarly journals Sample-level sound synthesis with recurrent neural networks and conceptors

2019 ◽  
Vol 5 ◽  
pp. e205 ◽  
Author(s):  
Chris Kiefer
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Synthesis Method ◽  
Network Models ◽  
Sound Synthesis ◽  
Boolean Logic ◽  
Training Data ◽  
Sound Design ◽  
Echo State Networks ◽  
Granular Synthesis

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.

Improvement of accuracy in a sound synthesis method using Evolutionary Product Unit Networks

2013 ◽  
Vol 40 (5) ◽  
pp. 1477-1483 ◽  
Author(s):  
M. Dolores Redel-Macías ◽  
Francisco Fernández-Navarro ◽  
Pedro A. Gutiérrez ◽  
A. José Cubero-Atienza ◽  
César Hervás-Martínez
Keyword(s):  
Synthesis Method ◽  
Sound Synthesis ◽  
Evolutionary Product

Driving Sound Synthesis with a Live Audio Signal

2011 ◽  
pp. 167-194
Author(s):  
Cornelius Poepel
Keyword(s):  
Empirical Study ◽  
Human Computer Interaction ◽  
Synthesis Method ◽  
Audio Signal ◽  
Sound Synthesis ◽  
Synthesis Algorithm ◽  
User Input ◽  
String Instrument ◽  
Computer Interaction

An overview on problems and methods to map performers’ actions to a synthesized sound is presented. Approaches incorporating the audio signal are described and a synthesis method called “Audio Signal Driven Sound Synthesis” is introduced. It uses the raw audio signal of a traditional instrument to drive a synthesis algorithm. The system tries to support musicians with satisfying instrument-specific playability. In contrast to common methods that try to increase openness for the player’s input, openness of the system is achieved here by leaving essential playing parameters non-formalized as far as possible. Three implementations of the method and one application are described. An empirical study and experiences with users testing the system implemented for a bowed string instrument are presented. This implementation represents a specific case of a broader range of approaches to the treatment of user input, which have applications in a wide variety of contexts involving human-computer interaction.

scholarly journals Sample-level sound synthesis with recurrent neural networks and conceptors

2018 ◽  
Author(s):  
Chris Kiefer
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Frequency Control ◽  
Synthesis Method ◽  
Sound Synthesis ◽  
Boolean Logic ◽  
Training Data ◽  
Reservoir Computing ◽  
Research Questions ◽  
Granular Synthesis

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 and procedural audio but has yet to be explored. Two novel methods of sound synthesis based on conceptors are 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. Conceptillators are trainable, pitch-controlled oscillators for harmonically rich waveforms, commonly used in a variety of sound synthesis applications. Both systems can exploit conceptor pattern morphing, boolean logic and manipulation of RNN dynamics, enabling new creative sonic possibilities. Experiments reveal how RNN runtime parameters can be used for pitch-independent timestretching and for precise frequency control of cyclic waveforms. They show how these techniques can create highly malleable sound synthesis models, trainable using short sound samples. Limitations are revealed with regards to reproduction quality, and pragmatic limitations are also shown, where exponential 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; future possibilities and research questions are outlined, including possibilities in generative sound.

Gestural Control of Sound Synthesis

2004 ◽  
Vol 92 (4) ◽  
pp. 632-644 ◽  
Author(s):  
M.M. Wanderley ◽  
P. Depalle
Keyword(s):  
Sound Synthesis ◽  
Gestural Control
Sign in / Sign up

Export Citation Format

Share Document