Recognition of music types

Author

Soltau, Hagen ; Schultz, Tanja ; Westphal, Martin ; Waibel, Alex

Author_Institution

Karlsruhe Univ., Germany

Volume

2

fYear

1998

fDate

12-15 May 1998

Firstpage

1137

Abstract

This paper describes a music type recognition system that can be used to index and search in multimedia databases. A new approach to temporal structure modeling is supposed. The so called ETM-NN (explicit time modelling with neural network) method uses abstraction of acoustical events to the hidden units of a neural network. This new set of abstract features representing temporal structures, can be then learned via a traditional neural networks to discriminate between different types of music. The experiments show that this method outperforms HMMs significantly

Keywords

acoustic signal processing; audio signals; feature extraction; hidden Markov models; learning (artificial intelligence); multimedia computing; music; neural nets; ETM-NN method; HMM; abstract features; acoustical events abstraction; experiments; explicit time modelling with neural network; hidden units; multimedia database indexing; multimedia database searching; music type recognition system; neural network; temporal structure modeling; temporal structures; Cepstral analysis; Hidden Markov models; Indexes; Interactive systems; Laboratories; Multimedia databases; Multiple signal classification; Music; Neural networks; Speech;

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.1998.675470

Filename

675470