中大學術數位典藏-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 987654321/106564
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 94201/94201 (100%)
造访人次 : 81595444      在线人数 : 3232
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/106564


    题名: An acoustic feature-based similarity scoring system for speech rehabilitation assistance
    作者: 吳炤民;Syauqy, Dahnial;Wu, Chao-Min;Setyawati, Onny
    贡献者: 資訊電機學院電機工程學系
    关键词: Adolescent;Adult;Algorithms;Child;Child, Preschool;Classification;Computer-assisted speech therapy;Cooperation;Female;Formants;Fricatives;Humans;Male;Middle Aged;Mothers;multilayer perceptron;Patients;Pitch;Pitch Perception;Rehabilitation;Respondents;Robustness;Scores;Sound intensity;Speech;speech disorder;speech processing;Speech therapy;Speech Therapy - instrumentation;Speech Therapy - methods;strident fricative detection;Therapy, Computer-Assisted - instrumentation;Therapy, Computer-Assisted - methods;Veterans;Vowels;Young Adult
    日期: 2016-08-17
    上传时间: 2026-04-23 13:28:56 (UTC+8)
    出版者: Taylor and Francis Ltd.;England: Taylor & Francis
    摘要: 摘要: The purpose of this study is to develop a tool to assist speech therapy and rehabilitation, which focused on automatic scoring based on the comparison of the patient's speech with another normal speech on several aspects including pitch, vowel, voiced-unvoiced segments, strident fricative and sound intensity. The pitch estimation employed the use of cepstrum-based algorithm for its robustness; the vowel classification used multilayer perceptron (MLP) to classify vowel from pitch and formants; and the strident fricative detection was based on the major peak spectral intensity, location and the pitch existence in the segment. In order to evaluate the performance of the system, this study analyzed eight patient's speech recordings (four males, four females; 4-58-years-old), which had been recorded in previous study in cooperation with Taipei Veterans General Hospital and Taoyuan General Hospital. The experiment result on pitch algorithm showed that the cepstrum method had 5.3% of gross pitch error from a total of 2086 frames. On the vowel classification algorithm, MLP method provided 93% accuracy (men), 87% (women) and 84% (children). In total, the overall results showed that 156 tool's grading results (81%) were consistent compared to 192 audio and visual observations done by four experienced respondents. Implication for Rehabilitation Difficulties in communication may limit the ability of a person to transfer and exchange information. The fact that speech is one of the primary means of communication has encouraged the needs of speech diagnosis and rehabilitation. The advances of technology in computer-assisted speech therapy (CAST) improve the quality, time efficiency of the diagnosis and treatment of the disorders. The present study attempted to develop tool to assist speech therapy and rehabilitation, which provided simple interface to let the assessment be done even by the patient himself without the need of particular knowledge of speech processing while at the same time, also provided further deep analysis of the speech, which can be useful for the speech therapist.
    其他題名: Disabil Rehabil Assist Technol
    出版者: England: Taylor & Francis
    出版日期: 2016-08-17
    出處: Disability and rehabilitation: Assistive technology, 2016-08, Vol.11 (6), p.501-515
    版權: 2015 Informa UK Ltd. 2015
    識別號: ISSN: 1748-3107
    識別號: ISSN: 1748-3115
    識別號: EISSN: 1748-3115
    識別號: DOI: 10.3109/17483107.2015.1027297
    識別號: PMID: 25847198
    显示于类别:[電機工程學系] 期刊論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    index.html0KbHTML12检视/开启


    在NCUIR中所有的数据项都受到原著作权保护.

    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