Abstract:
We evaluate the hidden neural network HMM/NN hybrid on two speech recognition benchmark tasks; (1) task independent isolated word recognition on the Phonebook database, a...View moreMetadata
Abstract:
We evaluate the hidden neural network HMM/NN hybrid on two speech recognition benchmark tasks; (1) task independent isolated word recognition on the Phonebook database, and (2) recognition of broad phoneme classes in continuous speech from the TIMIT database. It is shown how hidden neural networks (HNNs) with much fewer parameters than conventional HMMs and other hybrids can obtain comparable performance, and for the broad class task it is illustrated how the HNN can be applied as a purely transition based system, where acoustic context dependent transition probabilities are estimated by neural networks.
Date of Conference: 15-15 May 1998
Date Added to IEEE Xplore: 06 August 2002
Print ISBN:0-7803-4428-6
Print ISSN: 1520-6149