Files in this item

FilesDescriptionFormat

application/pdf

application/pdfDi_He.pdf (611kB)Restricted to U of Illinois
(no description provided)PDF

Description

Title:Accelerating lattice scoring of automatic speech recognition through acoustic pre-pruning on GPU
Author(s):He, Di
Advisor(s):Chen, Deming
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Degree:M.S.
Genre:Thesis
Subject(s):acoustic pre-pruning
lattice scoring
Gaussian mixture model (GMM)
graphic processing unit (GPU)
Abstract: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.
Issue Date:2015-01-21
URI:http://hdl.handle.net/2142/73019
Rights Information:Copyright 2014 Di He
Date Available in IDEALS:2015-01-21
Date Deposited:2014-12


This item appears in the following Collection(s)

Item Statistics