Beat tracking with a two state model [music applications]

Author

Davies, M.E.P. ; Plumbley, M.D.

Author_Institution

Centre for Digital Music, London Univ., UK

Volume

3

fYear

2005

fDate

23-23 March 2005

Abstract

In this paper we apply a two state switching model to the problem of audio based beat tracking. Our analysis is based around the generation and application of adaptively weighted comb filterbank structures to extract beat timing information from the midlevel representation of an input audio signal known as the onset detection function. We evaluate our system using a previously published dataset (S. Hainsworth, Ph.D. thesis, Cambridge Univ., 2004), and in performing a direct comparison with the current state of the art, present comparable results.

Keywords

adaptive filters; audio signal processing; comb filters; music; signal representation; state-space methods; adaptively weighted comb filterbank structures; audio signal mid-level representation; beat alignment; beat period estimation; beat timing information extraction; context dependent model; musical audio signal beat tracking; onset detection function; state space switching model; two state switching model; Adaptive signal detection; Context modeling; Data mining; Filter bank; Humans; Information analysis; Signal analysis; Signal generators; Signal processing; Timing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on

Conference_Location

Philadelphia, PA

ISSN

1520-6149

Print_ISBN

0-7803-8874-7

Type

conf

DOI

10.1109/ICASSP.2005.1415691

Filename

1415691