Reduced-Rank Spectra and Minimum Entropy Priors for Generalized Sound Recognition

Casey, Michael A.. 2001. 'Reduced-Rank Spectra and Minimum Entropy Priors for Generalized Sound Recognition'. In: Workshop on Consistent and Reliable Cues for Sound Analysis,. Aalborg, Denmark. [Conference or Workshop Item]

No full text available

Abstract or Description

We propose a generalized sound recognition system that uses reduced-dimension log-spectral features and a minimum entropy hidden Markov model classifier. The proposed system addresses the major challenges of generalized sound recognition—namely, selecting robust acoustic features and finding models that perform well across diverse sound types.
To test the generality of the methods, we sought sound classes consisting of time-localized events, sequences, textures and mixed scenes. In other words, no assumptions on signal composition were imposed on the corpus.
Comparison between the proposed system and conventional maximum likelihood training showed that minimum entropy models yielded superior performance in a 20-class recognition experiment. The experiment tested discrimination between speech, non-speech utterances, environmental sounds, general sound effects, animal sounds, musical instruments and commercial music recordings.

Item Type:

Conference or Workshop Item (Paper)

Related URLs:

Departments, Centres and Research Units:



September 2001Published

Event Location:

Aalborg, Denmark

Item ID:


Date Deposited:

01 Dec 2015 15:43

Last Modified:

20 Jun 2017 09:43


Edit Record Edit Record (login required)