跳到主要內容

臺灣博碩士論文加值系統

(18.204.48.69) 您好!臺灣時間:2021/07/28 00:08
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:凃昱銘
研究生(外文):Yu-Ming Tu
論文名稱:基於快速音高序列比對之哼唱式歌曲檢索
論文名稱(外文):Query-by-humming Retrieval of Songs Based on Fast Pitch Sequence Matching
指導教授:蔡偉和蔡偉和引用關係
口試委員:尤信程張智星
口試日期:2012-01-13
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:電腦與通訊研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2012
畢業學年度:100
語文別:中文
論文頁數:32
中文關鍵詞:動態時間伸縮快速傅立業轉換音樂資訊檢索
外文關鍵詞:dynamic time warpingfast Fourier transformquery-by-hummingquery-by-singing
相關次數:
  • 被引用被引用:2
  • 點閱點閱:142
  • 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:1
本篇論文為針對傳統音樂資訊檢索的檢索部分做加速的研究。在傳統的音樂資訊檢索裡,是利用動態時間伸縮(Dynamic Time Warping;DTW)來做檢索的動作,雖然DTW 的辨識率很高,但是在執行上會花太多的時間,使得當歌曲資料庫非常龐大時,會變得非常沒有效率。而為了克服DTW 沒有效率的問題,在過去有很多人也對此一問題做過研究,例如:改變DTW 的演算方法、使用兩階段辨識的方法…等。而在本篇論文中,採用的也是兩階段辨識的方法,只不過第一階段是採用快速傅立葉轉換(Fast Fourier Transform;FFT)來做篩選的動作,而在第二階段依然採用DTW 來做更精確的比對,我們希望透過這樣的方式來讓檢索的速度更快更精確。

As the concrete descriptions, such as title, singer or lyrics, cannot fully represent the abstract content of music, such as melody or emotion, it is often the case that people know what the song they want sounds like, but just cannot recall its title or lyrics. To overcome this problem, a promising solution is the so-called query-by- singing/humming (QBSH), which allows users to retrieve a song by simply singing or humming a fragment of the song. Although techniques on QBSH have been studied for more than one decade, they are still far from popular in real applications. This thesis investigates a QBSH method that enables fast melody comparison. The basic idea is to measure the distances between note sequences in the frequency domain instead of time domain. Thanks to the merit of fast Fourier transform, we can convert different-length note sequences into equal-dimension vectors via zero padding. The equal dimensionality allows us to compare the vectors using Euclidean distance directly, which avoids performing time-consuming alignment between sequences. To take both efficiency and effectiveness into account, the proposed fast melody comparison method is combined with dynamic time warping technique into a two-stage sequence matching system. Our experiments conducted using the MIREX 2006 database demonstrate the superiority of the proposed system over other existing systems.

中文摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 研究動機 1
1.2 相關研究 3
1.3 章節概要 4
第二章 音高追蹤 5
2.1 次諧波總和法 6
2.1.1 音框化 6
2.1.2 快速傅立葉轉換 7
2.1.3 頻率刻度轉換 8
2.1.4 計算次諧波總和 8
2.1.5 找出能量極大值 8
2.2 次諧波與諧波比 9
2.3 平均能量差異法 11
2.4 自相關函數法 12
2.5 使用動態規劃求取未知的音高序列 13
第三章 動態時間伸縮 14
第四章 基於FFT 之音樂檢索系統 17
4.1 系統架構 17
4.2 基於FFT 之快速序列匹配 19
4.3 系統複雜度分析 22
第五章 實驗結果 23
5.1 實驗素材 23
5.2 建立資料庫 25
5.2.1 Document 資料庫 25
5.2.2 Query 資料庫 25
5.3 系統評估公式 26
5.4 一階段J-DTW 辨識 26
5.5 兩階段J-DTW 辨識 27
5.6 音高序列減半之兩階段J-DTW 辨識 28
5.7 FFT—J-DTW 兩階段辨識 29
第六章 結論與未來展望 30
第七章 參考文獻 31

[1] J. Downie, K. West, A. Ehmann, and E. Vincent, "The 2005 music information
Retrieval evaluation exchange (MIREX 2005): Preliminary overview," in Proc
International Conference on Music Information Retrieval, London, UK, 2005,
pp. 320-323.
[2] H. M. Yu, W. H. Tsai, and H. M. Wang, "A query-by-singing technique for
retrieval polyphonic objects of popular music," in Proc. Asian Information
Retrieval Symp., 2005.
[3] H. M. Yu, W. H. Tsai, and H. M. Wang, "A Query-by-Singing for Retrieving
Karaoke Music," IEEE Trans. On Multimedia, vol. 10, no. 8, pp. 1626-1637,
Dec. 2008.
[4] Ghias, A., H. Logan, D. Chamberlin, and B. C. Smith, "Query by Humming:
Musical Information Retrieval in an Audio Database," in Proc. of Third ACM
International Conference on Multimedia, 1995, pp. 231-236.
[5] P. Hall and G. Dowing, "Approximate String Matching," ACM Computing
Survey, vol. 12, no. 4, pp. 381-402, Dec. 1980.
[6] Mo, J. S., C. H. Han, and Y. S. Kim, "A Melody-Based Similarity Computation
Algorithm for Musical Information," in Proc. of Knowledge and Data
Engineering Exchange Workshop (KDEX ''99), pp. 114 –121, 1999.
[7] Kosugi, N., Y. Nishihara, S. Kon’ya, M. Yamamuro, and K. Kushima, "Music
Retrieval by Humming," In Proceedings of PACRIM’99, pages 404-407, IEEE,
August 1999.
[8] Kosugi, N., Y. Nishihara, S. Kon’ya, M. Yamamuro, and K. Kushima, "A Practical
Query-By-Huming System for a Large Music Database," In Proc. ACM
Multimedia 2000.
[9] Jang. J.-S. Roger, Lee. Hong-Ru, and Kao. Ming-Yang, "Content-based Music
Retrieval Using Linear Scaling and Branch-and-bound Tree Search," IEEE
International Conference on Multimedia and Expo, Waseda University, Tokyo,
Japan, August. 2001.
[10] 李念容 "哼唱檢索的辨識方法改進及探討"
[11] D. Hermes, "Measurement of pitch by sub-harmonics summation," Journal of
Acoustics of Society of America, Am 83(1), January. 1988, pp. 257-264.
[12] X. Sun, "A Pitch Determination Algorithm Based on
Subharmonic-to-Harmonic Ratio," Proceedings of 6th International Conference
on Spoken Language Processing, Beijing, China, 2000.
[13] M. J. Ross, H. L. Shaffer, A. Cohen, R. Freudberg, and H. J. Manley, "Average
magnitude difference function pitch Extractor," IEEE Trans. Acousric, Speech,
and Signal Processing, vol. 22, pp. 353-362, Oct,1974.
[14] L. R. Rabiner, "On the Use of Autocorrelation Analysis for Pitch Detection,"
IEEE Trans. Acoustics, Speech, and Signal Processing, vol. 25, pp. 24-33, Feb.
1977.
[15] Jiang. Chun-Chen and Jang. J.-S. Roger, "TRUES: Tone Recognition Using
Extended Segments" National Tsing Hua University, Taiwan.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top