{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/35957"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/35957","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Personalized Computer Architecture as Contextual Partitioning for Speech Recognition","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.","abstract_html":"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.","abstract_has_math":false,"creators":["Kent, Christopher Grant"],"institution":"Virginia Tech","degree_name":"Master of Science","degree_level":"masters","degree_discipline":"Electrical and Computer Engineering","degree_department":"Electrical and Computer Engineering","school":null,"contributors":[],"advisors":[],"committee_chairs":["Paul, JoAnn M."],"committee_members":["Plassmann, Paul E.","Baumann, William T."],"year":2009,"date_issued":"2009-11-20","date_published":"2009-11-20","updated_at":"2026-07-22T22:20:25Z","subjects":["Brain Modeling","Language Processing","Mobile Computing","Parallel Processing","Parallel Architectures"],"languages":[],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-12042009-002644"],"render_values":[{"text":"etd-12042009-002644","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10919/35957","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Paul, JoAnn M."]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Plassmann, Paul E.","Baumann, William T."]},{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering"]},{"key":"dc:creator","label":"Author","values":["Kent, Christopher Grant"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2014-03-14T20:48:56Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2014-03-14T20:48:56Z","2010-01-22"]},{"key":"dc:date.issued","label":"Date","values":["2009-11-20"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical and Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Brain Modeling","Language Processing","Mobile Computing","Parallel Processing","Parallel Architectures"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["etd-12042009-002644"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10919/35957"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["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."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:title","label":"Title","values":["Personalized Computer Architecture as Contextual Partitioning for Speech Recognition"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Paul, JoAnn M."],"dc:contributor.committeemember":["Plassmann, Paul E.","Baumann, William T."],"dc:contributor.department":["Electrical and Computer Engineering"],"dc:creator":["Kent, Christopher Grant"],"dc:date.accessioned":["2014-03-14T20:48:56Z"],"dc:date.available":["2014-03-14T20:48:56Z","2010-01-22"],"dc:date.issued":["2009-11-20"],"dc:description.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."],"dc:description.degree":["Master of Science"],"dc:identifier.other":["etd-12042009-002644"],"dc:identifier.uri":["http://hdl.handle.net/10919/35957"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Brain Modeling","Language Processing","Mobile Computing","Parallel Processing","Parallel Architectures"],"dc:title":["Personalized Computer Architecture as Contextual Partitioning for Speech Recognition"],"dc:type":["Thesis"],"thesis:degree_discipline":["Electrical and Computer Engineering"],"thesis:degree_level":["masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:20:25Z"}