Rejection of extraneous input in speech recognition applications, using multi-layer perceptrons and the trace of HMMs
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 93-96 vol.1
- https://doi.org/10.1109/icassp.1991.150286
Abstract
In isolated-word recognition from everyday speech, a considerable share of the input lies outside the permitted vocabulary, and has to be rejected. The authors trained multilayer perceptrons to confirm or reject the choice made by a Markov model system during recognition by classifying the trace of the winning model. This rejection method is totally independent of the recognition procedure. Results show that performance on a database containing field data is better than with other rejection procedures.Keywords
This publication has 2 references indexed in Scilit:
- A new network-based speaker-independent connected-word recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Speaker hierarchical clustering for improving speaker-independent HMM word recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002