Phoneme recognition: neural networks vs. hidden Markov models vs. hidden Markov models
- 6 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 107-110 vol.1
- https://doi.org/10.1109/icassp.1988.196523
Abstract
A time-delay neural network (TDNN) for phoneme recognition is discussed. By the use of two hidden layers in addition to an input and output layer it is capable of representing complex nonlinear decision surfaces. Three important properties of the TDNNs have been observed. First, it was able to invent without human interference meaningful linguistic abstractions in time and frequency such as formant tracking and segmentation. Second, it has learned to form alternate representations linking different acoustic events with the same higher level concept. In this fashion it can implement trading relations between lower level acoustic events leading to robust recognition performance despite considerable variability in the input speech. Third, the network is translation-invariant and does not rely on precise alignment or segmentation of the input. The TDNNs performance is compared with the best of hidden Markov models (HMMs) on a speaker-dependent phoneme-recognition task. The TDNN achieved a recognition of 98.5% compared to 93.7% for the HMM, i.e., a fourfold reduction in error.<>Keywords
This publication has 6 references indexed in Scilit:
- BYBLOS: The BBN continuous speech recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- Neural computation by concentrating information in time.Proceedings of the National Academy of Sciences, 1987
- Learning representations by back-propagating errorsNature, 1986
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- Continuous speech recognition by statistical methodsProceedings of the IEEE, 1976