Data selection and model combination in connectionist speech recognition
The hybrid connectionist-hidden Markov model (HMM) approach to large vocabulary continuous speech recognition has been shown to be competitive with HMM based systems. However, the recent availability of extremely large amounts of acoustic training data has highlighted a problem with the connectionis...
| Main Author: | |
|---|---|
| Published: |
University of Cambridge
1997
|
| Subjects: | |
| Online Access: | http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.597919 |