Herein I document my exploration into the intersection of convolutional neural networks and raw non-lexical audio signals by detailing the development and results of four projects, each representing a unique problem in this domain: mutation detection, upscaling, classification, and generation. Convolutional neural networks, within the class of computational models which approximate a functional relationship between spaces of data expressed through a bio-inspired structure of modular interconnected neural nodes, are a subcategory suited to data with features that are spatially correlated while variable in absolute position. Dilated convolutional neural networks are of particular interest for operating on audio signals, as the exponential dilation stack both greatly expands the receptive field and extracts features at a progression which reflects the logarithmic properties of human hearing. More generally, I seek to study at a granular level the application of convolutional neural networks to any discrete temporal signals with dense periodic features, though the primary focus is on music and components of audio composition for music and video game production.
Identifer | oai:union.ndltd.org:unt.edu/info:ark/67531/metadc2356129 |
Date | 07 1900 |
Creators | Johnson, Violet Isabelle |
Contributors | Parberry, Ian, Doran, Jonathon, Akl, Robert, Nielsen, Rodney |
Publisher | University of North Texas |
Source Sets | University of North Texas |
Language | English |
Detected Language | English |
Type | Thesis or Dissertation |
Format | Text |
Rights | Public, Johnson, Violet Isabelle, Copyright, Copyright is held by the author, unless otherwise noted. All rights Reserved. |
Page generated in 0.0019 seconds