Shared more. Cited more. Safe forever.
    • advanced search
    • submit works
    • about
    • help
    • contact us
    • login
    View Item 
    •   MOspace Home
    • University of Missouri-Columbia
    • Graduate School - MU Theses and Dissertations (MU)
    • Theses and Dissertations (MU)
    • Dissertations (MU)
    • 2006 Dissertations (MU)
    • 2006 MU dissertations - Freely available online
    • View Item
    •   MOspace Home
    • University of Missouri-Columbia
    • Graduate School - MU Theses and Dissertations (MU)
    • Theses and Dissertations (MU)
    • Dissertations (MU)
    • 2006 Dissertations (MU)
    • 2006 MU dissertations - Freely available online
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    advanced searchsubmit worksabouthelpcontact us

    Browse

    All of MOspaceCommunities & CollectionsDate IssuedAuthor/ContributorTitleIdentifierThesis DepartmentThesis AdvisorThesis SemesterThis CollectionDate IssuedAuthor/ContributorTitleIdentifierThesis DepartmentThesis AdvisorThesis Semester

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular AuthorsStatistics by Referrer

    Statistical optimization of acoustic models for large vocabulary speech recognition

    Hu, Rusheng, 1971-
    View/Open
    [PDF] public.pdf (2.065Kb)
    [PDF] short.pdf (12.81Kb)
    [PDF] research.pdf (1.041Mb)
    Date
    2006
    Format
    Thesis
    Metadata
    [+] Show full item record
    Abstract
    This dissertation investigates optimization of acoustic models in speech recognition. Two new optimization methods are proposed for phonetic decision tree (PDT) search and Hidden Markov modeling (HMM)-- the knowledge-based adaptive PDT algorithm and the HMM gradient boosting algorithm. Investigations are conducted to applying both methods to improve word error rate of the state-of-the-art speech recognition system. However, these two methods are developed in a general machine learning background and their applications are not limited to speech recognition. The HMM gradient boosting method is based on a function approximation scheme from the perspective of optimization in function space rather than the parameter space, based on the fact that the Gaussian mixture model in each HMM state is an additive model of homogeneous functions (Gaussians). It provides a new scheme which can jointly optimize model structure and parameters. Experiments are conducted on the World Street Journal (WSJ) task and good improvements on word error rate are observed. The knowledge-based adaptive PDT algorithm is developed under a trend toward knowledge-based systems and aims at optimizing the mapping from contextual phones to articulatory states by maximizing implicit usage of the phonological and phonetic information, which is presumed to be contained in large data corpus. A computational efficient algorithm is developed to incorporate this prior knowledge in PDT construction. This algorithm is evaluated on the Telehealth conversational speech recognition and significant improvement on system performance is achieved.
    URI
    https://doi.org/10.32469/10355/4329
    https://hdl.handle.net/10355/4329
    Degree
    Ph. D.
    Thesis Department
    Computer science (MU)
    Rights
    OpenAccess.
    This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 License. Copyright held by author.
    Collections
    • 2006 MU dissertations - Freely available online
    • Computer Science electronic theses and dissertations (MU)

    Send Feedback
    hosted by University of Missouri Library Systems
     

     


    Send Feedback
    hosted by University of Missouri Library Systems