Abstract：Computer automatic accompaniment is studied from system viewpoint, and a computer system providing real-time accompaniment for electronic instrument is developed. The system includes two main modules: score-following and real-time accompaniment. To solve score-following problem, a dynamic programming algorithm is proposed based on extended window and reconstruction of matcher. The algorithm can locate input musical notes online in the score when the musical performance is full of errors compared to the score. To improve the quality of real-time accompaniment music, the bar is inducted as the unit of accompaniment and an accompaniment strategy is presented which determines how to add accompaniment online according to the location results. Experiment results demonstrate that the system has high performance in error resistance and real-time accompaniment expression.
[1] Bloch J J, Dannenberg R B. Real-Time Computer Accompaniment of Keyboard Performances // Proc of the International Computer Music Conference. Vancouver, Canada, 1985: 279-289 [2] Hidaka I, Goto M, Muraoka Y. An Automatic Jazz Accompaniment System Reacting to Solo // Proc of the International Computer Music Conference. Banff, Canada, 1995: 167-170 [3] Grubb L, Dannenberg R B. A Stochastic Method of Tracking a Vocal Performer // Proc of the International Computer Music Conference. Thessaloniki, Greece, 1997: 301-308 [4] Grubb L, Dannenberg R B. Enhanced Vocal Performance Tracking Using Multiple Information Sources // Proc of the International Computer Music Conference. Ann Arbor, USA, 1998: 37-44 [5] Raphael C. A Bayesian Network for Real-Time Musical Accompaniment // Dietterich T G, Becker S, Ghahramani Z, eds. Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 2002, 14: 1433-1439 [6] Aono Y, Katayose H, Inokuchi S. Development of a Session System with Acoustic Instruments. Electronics and Communications in Japan, 2001, 84(9): 20-30 [7] Puckette M. Score Following Using the Sung Voice // Proc of the International Computer Music Conference. Banff, Canada, 1995: 175-178 [8] Dannenberg R B. An Online Algorithm for Real-Time Accompaniment // Proc of the International Computer Music Conference. Paris, France, 1984: 193-198 [9] Pardo B, Birmingham W P. Following a Musical Performance from a Partially Specified Score // Proc of the Multimedia Technology Applications Conference. Irvine, USA, 2001: 202-207 [10] Pardo B, Birmingham W. Improved Score Following for Acoustic Performances // Proc of the International Computer Music Conference. Gteborg, Sweden, 2002: 262-265 [11] Large E W. Dynamic Programming for the Analysis of Serial Behaviors. Behavior Research Methods, Instruments and Computers, 1993, 25(2): 238-241 [12] Hoshishiba T, Horiguchi S, Fujinaga I. Study of Expression and Individuality in Music Performance Using Normative Data Derived from MIDI Recordings of Piano Music // Proc of the 4th International Conference on Music Perception and Cognition. Montreal, Canada, 1996: 465-470 [13] Heijink H, Desain P, Honing H, et al. Make Me a Match: An Evaluation of Different Approaches to Score-Performance Matching. Computer Music Journal, 2000, 24(1): 43-56
2008, Vol. 21 
