跳到主要內容

臺灣博碩士論文加值系統

(44.192.20.240) 您好!臺灣時間:2024/02/24 00:17
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:楊宇翔
研究生(外文):Yu-Siang Yang
論文名稱:哼唱式音樂檢索系統之容錯能力提升
論文名稱(外文):Enhancing Fault-Tolerance Capability for Query-by-Singing/Humming Musical Search System
指導教授:丁肇隆丁肇隆引用關係
指導教授(外文):Chao-Lung Ting
口試委員:王家輝呂承諭劉星劭
口試日期:2014-05-28
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:工程科學及海洋工程學研究所
學門:工程學門
學類:綜合工程學類
論文種類:學術論文
論文出版年:2014
畢業學年度:102
語文別:中文
論文頁數:85
中文關鍵詞:哼唱式音樂檢索雜訊濾除停頓處理音高調整節奏處理
外文關鍵詞:Query-by-Singing/HummingNoise filteringRest handlingPitch adjustmentTempo handing
相關次數:
  • 被引用被引用:1
  • 點閱點閱:318
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
隨著數位音樂數目的成長,如何正確且及時地從音樂資料庫中搜尋出特定的歌曲資訊,實為一項重要的課題。哼唱式音樂檢索(Query-by-Singing/Humming,簡稱QbSH)不同於以往利用文字為基礎的搜尋方式,其透過使用者哼唱歌曲的部分片段,從中計算隨時間變化的音高(Pitch)特徵,並與資料庫進行比對,以輸出最符合使用者哼唱的歌曲資訊。現今已有許多QbSH的相關研究和應用軟體,且對於使用者正確哼唱皆能提供良好之比對結果,然而,倘若使用者哼唱時受雜訊干擾,或其自身在停頓、音準、以及節奏出現錯誤,則目前的研究和軟體將難以處理上述多種錯誤情況。本研究提出一具容錯機制之QbSH系統,其透過系統架構和演算法設計,實現雜訊濾除、停頓處理、音高調整、以及節奏處理之容錯能力。本研究之比對結果,並與目前行動裝置中常用的QbSH應用軟體作比較,以驗證其優越性。

With the proliferation of digital music, there is an important topic on searching the accurate and specific song from music database and in a proper real-time. Query-by-Singing/Humming (QbSH) is a song search technique that differs from previous text-based search. It compute the time-varying pitch feature from user’s acoustic input, and compare with music database to generate the ranking list of similar songs. Related QbSH researches provide the good matched results only when user sang correctly. If user was interfered with noise when singing, or user occurs the rest, pitch, or tempo mistakes, current researches may not handles above conditions. A novel QbSH system with the design of new system architecture and algorithm has been proposed to achieve the fault-tolerance of noise, rest, pitch, and tempo. The experimental results achieved the superiority by comparing to current QbSH software.

口試委員會審定書 i
誌謝 ii
摘要 iii
ABSTRACT iv
論文目錄 v
圖目錄 viii
表目錄 x
第一章、緒論 1
1.1 研究動機與目的 1
1.2 研究貢獻 1
1.3 系統流程 2
1.4 論文架構 3
第二章、相關研究與方法 4
2.1 基本聲學特徵 4
2.2 音高追蹤 5
2.2.1 音框化 6
2.2.2 自相關函數 7
2.2.3 平均能量差異函數 9
2.2.4 倒頻譜 9
2.3 音高比對 10
2.3.1 線性伸縮 11
2.3.2 動態時間扭曲 12
第三章、音高追蹤器 15
3.1 音高追蹤 15
3.2 停頓處理 16
3.3 中位數濾波器 18
3.4 判斷是否過濾雜訊 20
3.5 預測頻率範圍 21
3.6 使用預測頻率範圍於訊號過濾 22
3.7 使用預測頻率範圍於音高追蹤 25
第四章、比對引擎 27
4.1 歌曲片段調整 28
4.2 音調移位 29
4.3 節奏處理 33
4.3.1 線性伸縮應用於節奏處理 34
4.3.2 動態時間扭曲應用於節奏處理 36
4.3.3 結合線性伸縮與動態時間扭曲應用於節奏處理 39
第五章、同步化流程 50
第六章、實驗結果與討論 52
6.1 實驗介紹 52
6.1.1 實驗平台 52
6.1.2 實驗資料庫 52
6.1.3 測試資料 53
6.1.4 實驗評估指標 54
6.2 實驗結果 54
6.2.1 音高追蹤方法之比較 54
6.2.2 各子系統之實驗結果 58
6.3 與QbSH應用軟體之比較結果 62
6.3.1 SoundHound應用軟體 62
6.3.2 比較說明 63
6.3.3 比較結果 67
第七章、結論與未來方向 70
參考文獻 71
附錄一 76
附錄二 85


[1]J. S. Downie, "Music information retrieval," Annual Review of Information Science and Technology, vol. 37, pp. 295-340, 2003.
[2]R. Typke, F. Wiering, and R. C. Veltkamp, "A Survey Of Music Information Retrieval Systems," presented at the IS MIR, 2005.
[3]A. Ghias, J. Logan, D. Chamberlin, and B. C. Smith, "Query by humming: musical information retrieval in an audio database," In ACM Multimedia, pp. 231-236, 1995.
[4]J. S. R. Jang and G. Ming-Yang, "A query-by-singing system based on dynamic programming," International Workshop on Intelligent Systems Resolution, pp. 85-89, 2000.
[5]A. Duda, A. Nurnberger, and S. Stober, "Towards Query by Singing/Humming on Audio Databases," presented at the IS MIR, 2007.
[6]Y. Hung-Ming, W. H. Tsai, and W. Hsin-min, "A Query-by-Singing System for Retrieving Karaoke Music," Multimedia, IEEE Transactions on, vol. 10, pp. 1626-1637, 2008.
[7]M. Antonelli, A. Rizzi, and G. del Vescovo, "A Query by Humming System for Music Information Retrieval," in Intelligent Systems Design and Applications (ISDA), 2010 10th International Conference on, 2010, pp. 586-591.
[8]F. Lin, Z. Xiaoyan, L. Yiwei, Y. Yuan, and J. Bo, "A similarity measure of Jumping Dynamic Time Warping," in Fuzzy Systems and Knowledge Discovery (FSKD), 2010 Seventh International Conference on, 2010, pp. 1677-1681.
[9]C. ZongChao, L. ChingShun, and C. YiHen, "Fast music information retrieval using PAT tree based dynamic time warping," in Information, Communications and Signal Processing (ICICS) 2011 8th International Conference on, 2011, pp. 1-5.
[10]J. Dalwon, S. Chat-Jong, S. Saim, P. Sung-Joo, J. Sei-Jin, and L. Seok-Pil, "Implementation of a matching engine for a practical query-by-singing/humming system," in Signal Processing and Information Technology (ISSPIT), 2011 IEEE International Symposium on, 2011, pp. 258-263.
[11]P. Sungjoo and C. Kwangsue, "Query by singing/hum ming (QbSH) system for polyphonic music retrieval," in Consumer Electronics (ICCE), 2012 IEEE International Conference on, 2012, pp. 245-246.
[12]鄭秀玲, 奇妙的聲音. 臺北市: 三民, 1994.
[13]上田昭, 春永裕子, and 林勝儀譯, 樂理 : 理論與應用. 臺北市: 美樂, 1997.
[14]H. M. Miller, P. Taylor, E. Williams, and 桂冠學術編輯室譯, 音樂概論. 臺北市: 桂冠, 1999.
[15]李重光, 音樂理論基礎 : 最權威的中文樂理教本. 臺北市: 世界文物, 2008.
[16]I. Peretz, E. Brattico, M. Jarvenpaa, and M. Tervaniemi, "The amusic brain: in tune, out of key, and unaware," Brain, vol. 132, pp. 1277-1286, May 1, 2009 2009.
[17]J. Dalwon, J. Sei-Jin, and L. Seok-Pil, "Test of pitch extraction algorithms for query-by-singing/humming system," in Broadband Multimedia Systems and Broadcasting (BMSB), 2012 IEEE International Symposium on, 2012, pp. 1-4.
[18]J. R. Deller, J.G.Proakis, and J. H. L. Hansen, "Discrete-time processing of speech signals," 1993.
[19]M. Ryynanen and A. Klapuri, "Query by humming of midi and audio using locality sensitive hashing," in Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on, 2008, pp. 2249-2252.
[20]L. Rabiner, "On the use of autocorrelation analysis for pitch detection," Acoustics, Speech and Signal Processing, IEEE Transactions on, vol. 25, pp. 24-33, 1977.
[21]M. Ross, H. Shaffer, A. Cohen, R. Freudberg, and H. Manley, "Average magnitude difference function pitch extractor," Acoustics, Speech and Signal Processing, IEEE Transactions on, vol. 22, pp. 353-362, 1974.
[22]A. M. Noll, "Cepstrum Pitch Determination," The Journal of the Acoustical Society of America, vol. 41, pp. 293-309, 1967.
[23]C. E. Lin, L. Shun-Li, S. Wei-Fu, and H. Ching-Lien, "Harmonic measurement and assessment in demand-side power system," in Industrial Electronics, Control, and Instrumentation, 1995., Proceedings of the 1995 IEEE IECON 21st International Conference on, 1995, pp. 469-473 vol.1.
[24]J. S. R. Jang, L. Hong-Ru, and K. Ming-Yang, "Content-based music retrieval using linear scaling and branch-and-bound tree search," in Multimedia and Expo, 2001. ICME 2001. IEEE International Conference on, 2001, pp. 289-292.
[25]G. Al-Naymat, S. Chawla, and J. Taheri, "SparseDTW: a novel approach to speed up dynamic time warping," presented at the Proceedings of the Eighth Australasian Data Mining Conference - Volume 101, Melbourne, Australia, 2009.
[26]T. Shimamura and H. Kobayashi, "Weighted autocorrelation for pitch extraction of noisy speech," Speech and Audio Processing, IEEE Transactions on, vol. 9, pp. 727-730, 2001.
[27]J. Astola and P. Kuosmanen, "Fundamentals of Nonlinear Digital Filtering," 1997.
[28]J.-S. R. Jang and H.-R. Lee, "Hierarchical filtering method for content-based music retrieval via acoustic input," presented at the Proceedings of the ninth ACM international conference on Multimedia, Ottawa, Canada, 2001.
[29]J.-S. R. Jang, H.-R. Lee, J.-C. Chen, and C.-Y. Lin, "Research and developments of a multi-modal MIR engine for commercial applications in East Asia1," Journal of the American Society for Information Science and Technology, vol. 55, pp. 1067-1076, 2004.
[30]李念容, "哼唱檢索的辨識方法改進及探討," 2007.
[31]H. Abdi, "Coefficient of variation," Encyclopedia of Research Design. SAGE Publications, Inc., Thousand Oaks, CA, pp. 169-171, 2010.
[32]G. Zhiyuan, W. Qiang, Y. Liang, L. Gang, and G. Jun, "Query by humming via hierarchical filters," in Pattern Recognition (ICPR), 2012 21st International Conference on, 2012, pp. 3021-3024.
[33]GenieSoft. (2008). Overture 4.0繁體中文版. Available: http://www.popiano.org/big5/piano/soft/001.htm
[34]K. Schutte. (2012). MATLAB and MIDI. Available: http://www.kenschutte.com/midi
[35]SoundHound Inc. Available: http://www.soundhound.com/
[36]SoundHound Inc. - Recent Highlights. Available: http://www.soundhound.com/index.php?action=s.reviews
[37]L. Tao, H. Xianglin, Y. Lifang, and Z. Pengju, "Query by Humming: Comparing Voices to Voices," in Management and Service Science, 2009. MASS ''09. International Conference on, 2009, pp. 1-4.


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top