A novel objective function for improved phoneme recognition using time delay neural networks
- 1 January 1989
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 235-241 vol.1
- https://doi.org/10.1109/ijcnn.1989.118586
Abstract
The authors present single- and multispeaker recognition results for the voiced stop consonants /b, d, g/ using time-delay neural networks (TDNN), a new objective function for training these networks, and a simple arbitration scheme for improved classification accuracy. With these enhancements a median 24% reduction in the number of misclassifications made by TDNNs trained with the traditional backpropagation objective function is achieved. This redundant results in /b, d, g/ recognition rates that consistently exceed 98% for TDNNs trained with individual speakers; it yields a 98.1% recognition rate for a TDNN trained with three male speakers.Keywords
This publication has 4 references indexed in Scilit:
- Consonant recognition by modular construction of large phonemic time-delay neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Phoneme recognition: neural networks vs. hidden Markov models vs. hidden Markov modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Phoneme recognition using time-delay neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Learning representations by back-propagating errorsNature, 1986