DocumentCode :
417778
Title :
Bayesian estimation of simultaneous musical notes based on frequency domain modelling
Author :
Kashino, Kunio ; Godsill, Simon J.
Author_Institution :
NTT Commun. Sci. Labs., Atsugi, Japan
Volume :
4
fYear :
2004
fDate :
17-21 May 2004
Abstract :
The paper proposes a Bayesian method for polyphonic music description. The method first divides an input audio signal into a series of sections called snapshots, and then estimates parameters such as fundamental frequencies and amplitudes of the notes contained in each snapshot. The parameter estimation process is based on a frequency domain modelling and Gibbs sampling. Experimental results obtained from audio signals of test note patterns are encouraging; the accuracy is better than 80% for the estimation of fundamental frequencies in terms of semitones and instrument names when the number of simultaneous notes is two.
Keywords :
Bayes methods; amplitude estimation; audio signal processing; frequency estimation; frequency-domain analysis; music; musical instruments; signal sampling; Bayesian estimation; Gibbs sampling; audio signal; frequency domain modelling; instrument names; note amplitude estimation; note fundamental frequency estimation; parameter estimation; polyphonic music description; semitones; simultaneous musical notes; test note patterns; Amplitude estimation; Bayesian methods; Frequency conversion; Frequency domain analysis; Frequency estimation; Instruments; Laboratories; Multiple signal classification; Music information retrieval; Parameter estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
ISSN :
1520-6149
Print_ISBN :
0-7803-8484-9
Type :
conf
DOI :
10.1109/ICASSP.2004.1326824
Filename :
1326824
Link To Document :
بازگشت