logo Idiap Research Institute        
 [BibTeX] [Marc21]
New Entropy Based Combination Rules in HMM/ANN Multi-stream ASR
Type of publication: Conference paper
Citation: misr03
Booktitle: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Year: 2003
Month: 4
Address: Hong Kong
Note: IDIAP-RR 2002 31
Crossref: misra-rr-02-31:
Abstract: Classifier performance is often enhanced through combining multiple streams of information. In the context of multi-stream HMM/ANN systems in ASR, a confidence measure widely used in classifier combination is the entropy of the posteriors distribution output from each ANN, which generally increases as classification becomes less reliable. The rule most commonly used is to select the ANN with the minimum entropy. However, this is not necessarily the best way to use entropy in classifier combination. In this article, we test three new entropy based combination rules in a full-combination multi-stream HMM/ANN system for noise robust speech recognition. Best results were obtained by combining all the classifiers having entropy below average using a weighting proportional to their inverse entropy.
Userfields: ipdmembership={speech},
Projects Idiap
Authors Misra, Hemant
Bourlard, Hervé
Tyagi, Vivek
Added by: [UNK]
Total mark: 0
  • misra_2003_icassp.pdf
  • misra_2003_icassp.ps.gz