Comparison of techniques for environmental sound recognition

被引：167

作者：

Cowling, M ^{[1
]}

Sitte, R ^{[1
]}

机构：

[1] Griffith Univ, Sch Informat Technol, Gold Coast Mail Ctr, Nathan, Qld 9726, Australia

来源：

PATTERN RECOGNITION LETTERS | 2003年 / 24卷 / 15期

关键词：

non-speech sound recognition; environmental sound recognition; audio signal processing; acoustic signal processing; joint time-frequency feature extraction;

D O I：

10.1016/S0167-8655(03)00147-8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a comprehensive comparative study of artificial neural networks, learning vector quantization and dynamic time warping classification techniques combined with stationary/non-stationary feature extraction for environmental sound recognition. Results show 70% recognition using mel frequency cepstral coefficients or continuous wavelet transform with dynamic time warping. (C) 2003 Elsevier B.V. All rights reserved.

引用

页码：2895 / 2907

页数：13

共 24 条

[1]

[Anonymous], 2000, SPEECH AUDIO SIGNAL

[2]

[Anonymous], NETLAB ALGORITHMS PA

[3]

[Anonymous], AUTOMATIC SPEECH SPE

[4] Computer identification of musical instruments using pattern recognition with cepstral coefficients as features [J].

Brown, JC .

JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1999, 105 (03) :1933-1941

[5]

CASTRO MJ, 1993, P EUR C SPEECH COMM, V3, P1599

[6]

Cohen L., 1995, TIME FREQUENCY ANAL

[7]

COWLING M, 2000, P MATL US C MELB AUS

[8]

COWLING M, 2002, P DSPCS 2002 MANL AU, V5

[9]

Cowling M, 2002, ADV SIGNAL PROCESSIN

[10]

COWLING M, 2001, P ICICS 2001 SING

← 1 2 3 →