Paper Info
Title
A state space model for online polyphonic audio-score alignment
Abstract
We present a novel online audio-score alignment approach for multi-instrument polyphonic music. This approach uses a 2-dimensional state vector to model the underlying score position and tempo of each time frame of the audio performance. The process model is defined by dynamic equations to transition between states. Two representations of the observed audio frame are proposed, resulting in two observation models: a multi-pitch-based and a chroma-based. Particle filtering is used to infer the hidden states from observations. Experiments on 150 music pieces with polyphony from one to four show the proposed approach outperforms an existing offline global string alignment-based score alignment approach. Results also show that the multi-pitch-based observation model works better than the chroma-based one.
Year
DOI
Venue
2011
10.1109/ICASSP.2011.5946374
ICASSP
Keywords
Field
DocType
hidden state,particle filtering (numerical methods),online polyphonic audio-score alignment,score following,particle filtering,online algorithm,music,online audio score alignment,multipitch based audio frame,realtime,audio-score alignment,multiinstrument polyphonic music,audio signal processing,chroma based audio frame,state space model,hidden markov model,real time systems,computer model,bayesian methods,mathematical model,bayesian method,computational modeling,estimation,hidden markov models
Online algorithm,State vector,Pattern recognition,Computer science,State-space representation,Particle filter,Speech recognition,Score following,Artificial intelligence,Polyphony,Audio signal processing,Hidden Markov model
Conference
ISSN
ISBN
Citations 
1520-6149 E-ISBN : 978-1-4577-0537-3
978-1-4577-0537-3
22
PageRank 
References 
Authors
0.95
14
2
Name
Order
Citations
PageRank
Zhiyao Duan130526.86
Bryan Pardo283063.92