中大機構典藏-NCU Institutional Repository-提供博碩士論文、考古題、期刊論文、研究計畫等下載:Item 987654321/63060
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 81570/81570 (100%)
Visitors : 47023124      Online Users : 189
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version


    Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/63060


    Title: 用類神經網路研究正常與病理中文說話之神經關聯性;Study of Neural Correlates on Normal and Pathological Chinese Production with Neural Network Model
    Authors: 吳炤民
    Contributors: 國立中央大學電機工程學系
    Keywords: 醫學工程
    Date: 2012-12-01
    Issue Date: 2014-03-17 14:18:05 (UTC+8)
    Publisher: 行政院國家科學委員會
    Abstract: 研究期間:10108~10207;Recent published report indicates that there are 2.5 million people with speech and hearing disorders in Taiwan. As aging of population and getting more attention of early intervention in our community increases, population with various degrees of speech and hearing disorders also increases. For people with speech disorders often suffer from congenital or acquired speech impairment that is involved with damage in speech articulators or brain, the diversity of cause results in expressive difficulties, stuttering, or even no speech competence. The main purpose of this study is to simulate Chinese normal speech production and speech disorders with a neural network model (Directions Into Velocities Articulator,DIVA model) that can measure articulatory movements of speech organs, analyze speech sounds, and display the simulated brain activity regions. Original DIVA model is a learning model which progressively acquires the relationship between speech motor actions and speech sounds but provides no function of speech perception. For the first year project, the modified SOM (Self-organizing) neural network model will be used to develop a speech perception mechanism for the original DIVA model; and the modified DIVA model will be able to show its corresponding brain activity regions. Then the modified DIVA model will be used to simulate normal Chinese speech production based on the coarticulation mechanism and its corresponding vowel formant transition properties. Additionally, we will verify the simulated articulatory movements of speech organs of the modified DIVA model with the measured results from speech electromagnetic articulograph (Wave, Northern Digital Inc, Canada). Finally, for the third year project, we will simulate Chinese pathological speech (stuttering) by adjusting the parameters of the modified DIVA model (ex., reduce the ratio of auditory feedback or increase the delay of neural transmission). The simulated results, such as articulatory movements of speech organs, analysis of speech sound, and the simulated brain activity regions, will be used to investigate the causes of stuttering and provide possibly useful application for stuttering rehabilitation.
    Relation: 財團法人國家實驗研究院科技政策研究與資訊中心
    Appears in Collections:[Department of Electrical Engineering] Research Project

    Files in This Item:

    File Description SizeFormat
    index.html0KbHTML380View/Open


    All items in NCUIR are protected by copyright, with all rights reserved.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明