How limited training data can allow a neural network to outperform an 'optimal' statistical classifier
- 13 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
No abstract availableKeywords
This publication has 8 references indexed in Scilit:
- A connectionist model for consonant-vowel syllable recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A new algorithm for the estimation of hidden Markov model parametersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The 'neural' phonetic typewriterComputer, 1988
- Speech Physiology, Speech Perception, and Acoustic PhoneticsPublished by Cambridge University Press (CUP) ,1988
- Learning representations by back-propagating errorsNature, 1986
- Recognition of Isolated Digits Using Hidden Markov Models With Continuous Mixture DensitiesAT&T Technical Journal, 1985
- Continuous speech recognition by statistical methodsProceedings of the IEEE, 1976
- The DRAGON system--An overviewIEEE Transactions on Acoustics, Speech, and Signal Processing, 1975