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...
Main Author: | Chris Kiefer |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2019-07-01
|
Series: | PeerJ Computer Science |
Subjects: | |
Online Access: | https://peerj.com/articles/cs-205.pdf |
Similar Items
-
Phase Space Reconstruction-Based Conceptor Network for Time Series Prediction
by: Zheng Xu, et al.
Published: (2019-01-01) -
Detection of Chaos Using Reservoir Computing Approach
by: Ali Rida Ismail, et al.
Published: (2022-01-01) -
Marine echo-sounding equipment
by: International Organization for Standardization
Published: (1991) -
Sound velocity propagation in multibeam echosounding data /
by: 353429 Lim, Teck Seng
Published: (2008) -
Depth error budget for multibeam echo sounding /
by: Yang, Cheng Zhong, 1985-, et al.
Published: (2009)