Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/111266
DC Field | Value | |
---|---|---|
dc.title | Multilayer perceptron postprocessor to Hidden Markov modeling for speech recognition | |
dc.contributor.author | Jin, Guo | |
dc.contributor.author | Chung, Lui Ho | |
dc.date.accessioned | 2014-11-27T09:46:23Z | |
dc.date.available | 2014-11-27T09:46:23Z | |
dc.date.issued | 1993 | |
dc.identifier.citation | Jin, Guo,Chung, Lui Ho (1993). Multilayer perceptron postprocessor to Hidden Markov modeling for speech recognition. Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing 2 : II-263. ScholarBank@NUS Repository. | |
dc.identifier.isbn | 0780309464 | |
dc.identifier.issn | 07367791 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/111266 | |
dc.description.abstract | In this paper, a new neural network postprocessor is introduced to enhance the classification capability of hidden Markov modeling for speech recognition. This postprocessor receives stimuli from not one but all word- HMMs for each word speech and does not require segmenting speech frames at subword level. A multilayer perceptron implementation has achieved 20% to 30% syllable error reduction in experiments reported here. | |
dc.source | Scopus | |
dc.type | Conference Paper | |
dc.contributor.department | INSTITUTE OF SYSTEMS SCIENCE | |
dc.description.sourcetitle | Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing | |
dc.description.volume | 2 | |
dc.description.page | II-263 | |
dc.description.coden | IPROD | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.