2026-09-19T19:15:52Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/73019 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Chen, Deming He, Di 2015-01-21T19:56:09Z 2015-01-21T19:56:09Z 2017-01-22T10:15:25Z 2014-12 2015-01-21 2014-12 This thesis introduces an acoustic pre-pruning algorithm that speeds up lattice scoring for GMM based ASR systems, and a constrained agglomerative clustering algorithm that makes it possible to maintain the advantage of the new algorithm in a GPU implementation. The implementation undergoes 2% to 6% degradation in PER while accelerating the runtime of lattice scoring by 45X to 60X over a traditional CPU implementation. Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2014-12-09T17:13:49Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 He_Di.docx: 209312 bytes, checksum: b9c9f0815ff0dd4bcd62fbc7e2dfe745 (MD5) He_Di.pdf: 611140 bytes, checksum: 83ffe02efcf57fc6104f0fcd700f756f (MD5) Made available in DSpace on 2015-01-21T19:56:09Z (GMT). No. of bitstreams: 2 Di_He.pdf: 611155 bytes, checksum: f2d746c5590a05c6681910c207d596cd (MD5) He_Di.docx: 209473 bytes, checksum: f3aa2b7599e5e5d72f157c25d1dccfd7 (MD5) Embargo set by: Seth Robbins for item 73208 Lift date: 2017-01-21T19:56:18Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system U of I Only Restriction Lifted for Item 73208 on 2017-01-22T10:15:25Z. http://hdl.handle.net/2142/73019 en Copyright 2014 Di He acoustic pre-pruning lattice scoring Gaussian mixture model (GMM) graphic processing unit (GPU) Accelerating lattice scoring of automatic speech recognition through acoustic pre-pruning on GPU text Electrical & Computer Eng 1933 Electrical & Computer Engr 1200 University of Illinois at Urbana-Champaign Thesis M.S. MS:Electr & Computer Eng-UIUC 10KS1200MS