The present work contributes to the field of generalized sound classification. We extensively examine the performance of the next three feature sets: a) MPEG-7 Audio Spectrum Projection, b) MFCC (using an alternative method for their extraction) and c) a group derived utilizing critical band based wavelet packets. Subsequently three types of tem poral feature integration strategies are applied on the extracted instant values: a) short-term statistics, b) spectral moments and c) two autoregressive functions. During the experimental phase, we organize ten sound classes using professional sound effects collections of high quality. The density of each category is approximated with left-right hidden Markov models. Comparable results with respect to all the feature sets as well as integration methods are provided, which demonstrate the superiority of the short-term statistics method.
Sound classification based on temporal feature integration / S. Ntalampiras, I. Potamitis, N. Fakotakis - In: 2010 4th International Symposium on Communications, Control and Signal Processing (ISCCSP)[s.l] : IEEE, 2010. - ISBN 9781424462858. - pp. 1-4 (( Intervento presentato al 4. convegno International Symposium on Communications, Control, and Signal Processing tenutosi a Limassol nel 2010 [10.1109/ISCCSP.2010.5463315].
Sound classification based on temporal feature integration
S. Ntalampiras;
2010
Abstract
The present work contributes to the field of generalized sound classification. We extensively examine the performance of the next three feature sets: a) MPEG-7 Audio Spectrum Projection, b) MFCC (using an alternative method for their extraction) and c) a group derived utilizing critical band based wavelet packets. Subsequently three types of tem poral feature integration strategies are applied on the extracted instant values: a) short-term statistics, b) spectral moments and c) two autoregressive functions. During the experimental phase, we organize ten sound classes using professional sound effects collections of high quality. The density of each category is approximated with left-right hidden Markov models. Comparable results with respect to all the feature sets as well as integration methods are provided, which demonstrate the superiority of the short-term statistics method.File | Dimensione | Formato | |
---|---|---|---|
05463315.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
2.84 MB
Formato
Adobe PDF
|
2.84 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.