Bayesian classification of acoustical waveforms under environmental variability

Author

Christensen, Jens E N ; Godsill, Simon J.

Author_Institution

Dept. of Eng., Cambridge Univ., Cambridge, UK

fYear

2011

fDate

16-19 Oct. 2011

Firstpage

281

Lastpage

284

Abstract

We present in this paper a new multivariate probabilistic approach to Acoustic Pulse Recognition (APR) for tangible interface applications. This model uses Principle Component Analysis (PCA) in a probabilistic framework to classify tapping pulses with a high degree of variability. It was found that this model, achieves a higher robustness to pulse variability than simpler template matching methods, specifically when allowed to train on data containing high variability.

Keywords

Bayes methods; acoustic signal processing; principal component analysis; probability; signal classification; APR; Bayesian classification; PCA; acoustic pulse recognition; acoustical waveforms; environmental variability; multivariate probabilistic approach; principle component analysis; pulse variability; template matching methods; Acoustics; Principal component analysis; Signal processing algorithms; Testing; Training; Training data; Vectors; Acoustic pulse recognition; Bayesian classification; PCA; tangible interface;

fLanguage

English

Publisher

ieee

Conference_Titel

Applications of Signal Processing to Audio and Acoustics (WASPAA), 2011 IEEE Workshop on

Conference_Location

New Paltz, NY

ISSN

1931-1168

Print_ISBN

978-1-4577-0692-9

Electronic_ISBN

1931-1168

Type

conf

DOI

10.1109/ASPAA.2011.6082283

Filename

6082283