Minimum detection error training for acoustic signal monitoring

Author

Watanabe, Hideyuki ; Matsumoto, Yuji ; Katagiri, Shigeru

Author_Institution

ATR Human Inf. Process. Res. Labs., Kyoto, Japan

Volume

2

fYear

1998

fDate

12-15 May 1998

Firstpage

1193

Abstract

In this paper we propose a novel approach to the detection of acoustic irregular signals using minimum detection error (MDE) training. The MDE training is based on the generalized probabilistic descent method, which was originally developed as a general concept for a discriminative pattern recognizer design. We demonstrate its fundamental utility by experiments in which several acoustic events are detected in a noisy environment

Keywords

acoustic noise; acoustic signal detection; error analysis; learning (artificial intelligence); monitoring; neural nets; MDE training; acoustic events; acoustic irregular signals; acoustic signal monitoring; generalized probabilistic descent method; minimum detection error training; noisy environment; Acoustic noise; Acoustic signal detection; Biomedical acoustics; Biomedical monitoring; Condition monitoring; Event detection; Model driven engineering; Pattern recognition; Signal design; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on

Conference_Location

Seattle, WA

ISSN

1520-6149

Print_ISBN

0-7803-4428-6

Type

conf

DOI

10.1109/ICASSP.1998.675484

Filename

675484