Title page for ETD etd-12042009-002644


Type of Document Master's Thesis
Author Kent, Christopher Grant
Author's Email Address ckent@vt.edu
URN etd-12042009-002644
Title Personalized Computer Architecture as Contextual Partitioning for Speech Recognition
Degree Master of Science
Department Electrical and Computer Engineering
Advisory Committee
Advisor Name Title
Paul, JoAnn M. Committee Chair
Baumann, William T. Committee Member
Plassmann, Paul E. Committee Member
Keywords
  • Brain Modeling
  • Language Processing
  • Mobile Computing
  • Parallel Processing
  • Parallel Architectures
Date of Defense 2009-11-20
Availability unrestricted
Abstract
Computing is entering an era of hundreds to thousands of processing elements per chip, yet no known parallelism form scales to that degree. To address this problem, we investigate the foundation of a computer architecture where processing elements and memory are contextually partitioned based upon facets of a user’s life. Such Contextual Partitioning (CP), the situational handling of inputs, employs a method for allocating resources, novel from approaches used in today’s architectures. Instead of focusing components on mutually exclusive parts of a task, as in Thread Level Parallelism, CP assigns different physical components to different versions of the same task, defining versions by contextual distinctions in device usage. Thus, application data is processed differently based on the situation of the user. Further, partitions may be user specific, leading to personalized architectures. Our focus is mobile devices, which are, or can be, personalized to one owner. Our investigation is centered on leveraging CP for accurate and real-time speech recognition on mobile devices, scalable to large vocabularies, a highly desired application for future user interfaces. By contextually partitioning a vocabulary, training partitions as separate acoustic models with SPHINX, we demonstrate a maximum error reduction of 61% compared to a unified approach. CP also allows for systems robust to changes in vocabulary, requiring up to 97% less training when updating old vocabulary entries with new words, and incurring fewer errors from the replacement. Finally, CP has the potential to scale nearly linearly with increasing core counts, offering architectures effective with future processor designs.
Files
  Filename       Size       Approximate Download Time (Hours:Minutes:Seconds) 
 
 28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access 
  Kent_CG_T_2009.pdf 8.09 Mb 00:37:28 00:19:16 00:16:51 00:08:25 00:00:43
  Kent_CG_T_2009_Copyright.pdf 190.49 Kb 00:00:52 00:00:27 00:00:23 00:00:11 00:00:01

Browse All Available ETDs by ( Author | Department )

dla home
etds imagebase journals news ereserve special collections
virgnia tech home contact dla university libraries

If you have questions or technical problems, please Contact DLA.