• Login
    View Item 
    •   Home
    • UA Graduate and Undergraduate Research
    • UA Theses and Dissertations
    • Dissertations
    • View Item
    •   Home
    • UA Graduate and Undergraduate Research
    • UA Theses and Dissertations
    • Dissertations
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of UA Campus RepositoryCommunitiesTitleAuthorsIssue DateSubmit DateSubjectsPublisherJournalThis CollectionTitleAuthorsIssue DateSubmit DateSubjectsPublisherJournal

    My Account

    LoginRegister

    About

    AboutUA Faculty PublicationsUA DissertationsUA Master's ThesesUA Honors ThesesUA PressUA YearbooksUA CatalogsUA Libraries

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Multi-Task and Transfer Learning in Low-Resource Speech Recognition

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    azu_etd_17345_sip1_m.pdf
    Size:
    7.512Mb
    Format:
    PDF
    Download
    Author
    Meyer, Josh
    Issue Date
    2019
    Keywords
    Automatic Speech Recognition
    Deep Neural Networks
    Low-Resource Languages
    Multi-Task Learning
    Transfer Learning
    Advisor
    Bever, Thomas G.
    Surdeanu, Mihai
    
    Metadata
    Show full item record
    Publisher
    The University of Arizona.
    Rights
    Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction, presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
    Embargo
    Release after 08/20/2020
    Abstract
    This thesis investigates methods for Acoustic Modeling in Automatic Speech Recog- nition, assuming limited access to training data in the target domain. The Acoustic Models of interest are Deep Neural Network Acoustic Models (in both the Hybrid and End-to-End approaches), and the target domains in question are either different languages or different speakers. Inductive bias is transfered from a source domain during training, via Multi-Task Learning or Transfer Learning. With regards to Multi-Task Learning, Chapter (5) presents experiments which explicitly incorporate linguistic knowledge (i.e. phonetics and phonology) into an auxiliary task during neural Acoustic Model training. In Chapter (6), I investigate Multi-Task methods which do not rely on expert knowledge (linguistic or otherwise), by re-using existing parts of the Hybrid training pipeline. In Chapter (7), new tasks are discovered using unsupervised learning. In Chapter (8), using the “copy-paste” Transfer Learning approach, I demonstrate that with an appropriate early-stopping criteria, cross-lingual transfer is possible to both large and small target datasets. The methods and intuitions which rely on linguistic knowledge are of interest to the Speech Recognition practitioner working in low-resource domains. These same sections may be of interest to the theoretical linguist, as a study of the relative import of phonetic categories in classification. To the Machine Learning practitioner, I hope to offer approaches which can be easily ported over to other classification tasks. To the Machine Learning researcher, I hope to inspire new ideas on addressing the small data problem.
    Type
    text
    Electronic Dissertation
    Degree Name
    Ph.D.
    Degree Level
    doctoral
    Degree Program
    Graduate College
    Linguistics
    Degree Grantor
    University of Arizona
    Collections
    Dissertations

    entitlement

     
    The University of Arizona Libraries | 1510 E. University Blvd. | Tucson, AZ 85721-0055
    Tel 520-621-6442 | repository@u.library.arizona.edu
    DSpace software copyright © 2002-2017  DuraSpace
    Quick Guide | Contact Us | Send Feedback
    Open Repository is a service operated by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.