政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/115091
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文笔数/总笔数 : 115406/146445 (79%)
造访人次 : 55011191      在线人数 : 20
RC Version 6.0 © 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


    请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/115091


    题名: 流行音樂的詞曲搭配推薦系統
    作者: 沈錳坤
    贡献者: 資訊科學系
    关键词: 詞式結構分析;曲式結構分析;詞曲搭配;推薦系統
    lyrics structure analysis;music structure analysis;lyrics music alignment;recommendation
    日期: 2013
    上传时间: 2017-12-08 15:08:22 (UTC+8)
    摘要: 本計劃透過分析詞曲搭配的規則、研究流行音樂的詞曲搭配推薦技術及詞曲對齊演算法。此外，本研究研發並實作了以曲找詞的舊曲新詞推薦系統：透過使用者輸入歌曲，由系統自動查詢適合搭配的歌詞，並以歌聲模擬軟體試唱。本研究也可以延伸為以詞找曲的舊詞新曲推薦系統：透過使用者輸入歌詞，由系統自動查詢適合搭配的歌曲。本計劃的研究成果，透過雲端服務，提供舊曲新詞、舊詞新曲的音樂加值應用。
    This project investigates the relationships between lyrics and music for Chinese popular song. We investigate the methods for music structure and lyrics structure analysis respectively and propose the alignment algorithm between a lyrics and a music object. For music structure analysis, we detect the music sentence based on Support Vector Machine and discover the music form by Non-negative Matrix Factorization of constructed Self Similarity Matrix of music sentences. For lyrics structure analysis, we considered four features, word count, Pinyin, Part-Of-Speech, and Word tone, to measure the similarity between lyrics sentences and construct the Self Similarity Matrix of lyrics sentences. The lyrics structure is analyzed by finding the cohesive blocks of the lyrics Self Similarity Matrix. Moreover, we proposed the dynamic programming algorithm to align a lyrics and a music object. We developed the lyrics recommendation system that recommends lyrics accompany well with the query music. Experimental results showed that the proposed approach performs well for Chinese popular song.
    關聯: 執行起迄：2013/08/01~2015/01/31
    102-2221-E-004-005
    数据类型: report
    显示于类别:[資訊科學系] 國科會研究計畫

    文件中的档案:

    档案 描述 大小格式浏览次数
    102-2221-E-004-005.pdf3480KbAdobe PDF21216检视/开启


    在政大典藏中所有的数据项都受到原著作权保护.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈