2026-09-19T15:30:11Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/98429 2023-07-11 col_2142_14787 col_2142_5131 com_2142_9630 com_2142_234 com_2142_5130

Levinson, Stephen E. Wagner, William Jacob 2017-09-29T17:57:10Z 2017-09-29T17:57:10Z 2017-07-20 2017-08 The degrees of freedom problem is ubiquitous within motor control arising out of the redundancy inherent in motor systems and raises the question of how control actions are determined when there exist infinitely many ways to perform a task. Speech production is a complex motor control task and suffers from this problem, but it has not drawn the research attention that reaching movements or walking gaits have. Motivated by the use of dimensionality reduction algorithms in learning muscle synergies and perceptual primitives that reflect the structure in biological systems, an approach to learning sensory-motor synergies via dynamic factor analysis for control of a simulated vocal tract is presented here. This framework is shown to mirror the articulatory phonology model of speech production and evidence is provided that articulatory gestures arise from learning an optimal encoding of vocal tract dynamics. Broad phonetic categories are discovered within the low-dimensional factor space indicating that sensory-motor synergies will enable application of reinforcement learning to the problem of speech acquisition. Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2017-09-29 without embargo terms The student, William Wagner, accepted the attached license on 2017-07-19 at 22:54. The student, William Wagner, submitted this Thesis for approval on 2017-07-19 at 23:23. This Thesis was approved for publication on 2017-07-20 at 09:16. DSpace SAF Submission Ingestion Package generated from Vireo submission #11542 on 2017-09-29 at 11:32:17 Made available in DSpace on 2017-09-29T17:57:10Z (GMT). No. of bitstreams: 2 WAGNER-THESIS-2017.pdf: 4466446 bytes, checksum: 839bf552b5d2ed6fe9b017033945704d (MD5) LICENSE.txt: 4211 bytes, checksum: 9ff5b1dc29e2f9a965d3e5b8ce9b4e03 (MD5) Previous issue date: 2017-07-20 application/pdf http://hdl.handle.net/2142/98429 en Copyright 2017 William Jacob Wagner Synergies Speech Vocal tract Sensory-motor primitives Articulatory speech synthesis Unsupervised learning of vocal tract sensory-motor synergies text text Mechanical Sci & Engineering Mechanical Engineering University of Illinois at Urbana-Champaign Thesis M.S.