|
|
Cano, P., A. Loscos, and J. Bonada. 1999.
Score-performance matching using HMMs.
In Proceedings of the International Computer Music Conference.
Score-performance matching system based on HMMs. Simpler than the Raphael model.
|
|
|
Dannenberg, R. B. 1984.
An on-line algorithm for real-time accompaniment.
In Proceedings of the International Computer Music Conference,
Paris, France, 193-98.
One of the seminal papers in score-performance matching. Uses a string-matching approach to align recognised musical events with a score representation. No probabilistic or statistical techniques.
|
|
|
Grubb, L., and R. B. Dannenberg. 1997.
A stochastic method for tracking a vocal performer.
In Proceedings of the International Computer Music Conference,
301-08.
Probabilistic score-following system that estimates a smooth probability distribution function over possible future onsets. Oriented toward vocal soloists.
|
|
|
Raphael, C. 1999.
Automatic segmentation of acoustic musical signals using hidden
Markov models.
IEEE Transactions on Pattern Analysis and Machine
Intelligence 21 (4): 360-70.
Detailed presentation of the onset estimation used in Music Plus One. Based on a hidden Markov model. Smart distinction between long-term variations in tempo and local variations in duration, i.e., rubato.
|
|
|
Raphael, C. 2001.
A probabilistic system for automatic musical accompaniment.
Journal of Computational and Graphical Statistics 10 (3):
487-512.
Most complete of several presentations of the Music Plus One system. Details the accompaniment (`Play') system only. Elaborate graphical model with five layers, each with its own musical interpretation. Succeeds on both the mathematical and musical fronts, reflecting the author's polyglot background.
|
|
|
Raphael, C. 2003.
Orchestral musical accompaniment from synthesized audio.
In Proceedings of the International Computer Music Conference.
Extends the Music Plus One system to use time-scaled audio rather than MIDI for synthesising the accompaniments. Uses the phase vocoder as `place holder' until time allows for a better time-scaled synthesis algorithm.
|
|
|
Schwarz, D., A. Cont, and N. Schnell. 2005.
From Boulez to ballads: Training IRCAM's score follower.
In Proceedings of the International Computer Music Conference,
Barcelona, Spain.
Presents the most recent incarnation of IRCAM's score follower. Based on HMMs. Does not model the music signal directly; rather, it models the probability of future events. Proves robust to different styles of music.
|
|
|
Vercoe, B. 1984.
The synthetic performer in the context of live performance.
In Proceedings of the International Computer Music Conference,
Paris, France, 199-200.
One of the seminal papers in score-performance matching. Very short and insufficient for implementation. Divides the accompaniment task into three primary sub-tasks (listening, performing, and learning) and the primary features needed for each.
|