Representational issues in a neural network model of syllable recognition
- 1 January 1989
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Methods of applying neural network-based methods to the perception of speech sounds are developed and examined. The authors briefly outline the network architecture and algorithms that they have found useful in implementing a consonant-vowel syllable recognizer. They review in detail the input representations used and present some simulations comparing the performance of their system with the different input representation combinations.Keywords
This publication has 6 references indexed in Scilit:
- Prediction of perceived phonetic distance from critical-band spectra: A first stepPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A connectionist model for consonant-vowel syllable recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- The 'neural' phonetic typewriterComputer, 1988
- Training methods for a connectionist model of consonant-vowel syllable recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Distinctive features, categorical perception, and probability learning: Some applications of a neural model.Psychological Review, 1977
- Subdivision of the Audible Frequency Range into Critical Bands (Frequenzgruppen)The Journal of the Acoustical Society of America, 1961