吉他即時和弦辨識與跟譜系統

Real-Time Guitar Chord Recognition and Score Following System

侯智維(Chih-Wei Hou)

指導教授 ： 陳恆佑

共同指導教授 ： 張克寧

國立暨南國際大學/科技學院/資訊工程學系/碩士(2010年)

https://doi.org/10.6837/NCNU.2010.00078

摘要

在這資訊科技發達的時代，我們越來越懂得如何用電腦來幫我們處理周遭事物，甚至我們也將音樂數位化並與電腦結合，將音樂做更有效的處理與應用。
吉他學習者通常都需要不斷的反覆練習他們左手的和弦按法，但對初學者來說，他們可能會覺得枯燥乏味，特別是在他們可能無法清楚了解他們正在彈的和弦是否有按正確，以及是否有走音的現象。因此我們開發了一個系統來幫助學習者在學吉他時，能以一個更有效率且更有趣的方式去幫助他們練習。
本篇論文提出了一個不同於以往和弦辨識的方法，成功結合了音高追蹤與和弦辨識二項技術。首先藉著音高追蹤方法找出和弦的組成音，並將其與要辨識的和弦比對，再將比對成功的和弦應用到跟譜系統上。系統提供兩個模式，第一個模式可讓使用者隨著自己的節拍彈奏，第二個需讓使用者跟著系統的節拍彈奏，如此一來，彈奏者就可以知道自己彈的和弦以及拍子是否正確。

關鍵字

和弦辨識 ； 音高追蹤 ； 跟譜系統

並列摘要

Guitar learners usually need to repeatedly practice on the positioning of the fingers on the left hand when pressing on the chords. But it may be tedious for beginners, especially when they do not know whether the pressed chords are right or not, or whether the pitch is off-key or not. Therefore, we designed an application to help them. We hope that this system can increase their interest and improve the learning rate of novice guitar players.
In this thesis, we propose a novel method for chord recognition which combines pitch detection and chord recognition techniques. The pitch detection algorithm finds the pitches of chord and compares them with target chord. Finally, we apply the result on score following. Our system provides two modes. The first, players can freely play the guitar. The second, players have to follow the tempo dictated by the system. Therefore, players can know whether the chord and tempo they played are right or not.

並列關鍵字

chord recognition ； pitch detection ； score following

參考文獻

[Boge63] B. P. Bogert, M. J. R. Healy, and J. W. Tukey (1963): "The Frequency Analysis of Time Series for Echoes: Cepstrum, Pseudo Autocovariance, Cross-Cepstrum and Saphe Cracking". Proceedings of the Symposium on Time Series Analysis (M. Rosenblatt, Ed) Chapter 15, 209-243. New York: Wiley.

[Dela01] De la Cuadra, P., Master, A., & Sapp, C. (2001). “Efficient pitch detection techniques for interactive music”. In Proceedings of the 2001 International Computer Music Conference, La Habana, Cuba.

[Jone94] Jones, George T. (1994). HarperCollins College Outline Music Theory. ISBN: 0-06-467168-2.

[Kerd07] C. Kerdvibulvech and H. Saito (2007), “Real-time guitar chord estimation by stereo cameras for supporting guitarists,” in Proceedings of the International Workshop on Advanced Image Technology (IWAIT '07), pp. 256–261, Bangkok, Thailand.

[Noll69] Noll, M (1969). Pitch determination of human speech by the harmonic product spectrum, the harmonic sum spectrum, and a maximum likelihood estimate. In Proceedings of the Symposium on Computer Processing in communications: 779-97.