http://scholars.ntou.edu.tw/handle/123456789/17076| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Jung-Hua Wang | en_US |
| dc.contributor.author | Jia-Hon Lin | en_US |
| dc.date.accessioned | 2021-06-09T07:18:43Z | - |
| dc.date.available | 2021-06-09T07:18:43Z | - |
| dc.date.issued | 1995-11 | - |
| dc.identifier.uri | http://scholars.ntou.edu.tw/handle/123456789/17076 | - |
| dc.description.abstract | An adaptive spatiotemporal neural network (ASTNN) capable of performing a near Bayesian speech recognizer is proposed. A tuning algorithm is introduced in the ASTNN to adjust the threshold parameters in order to maximize the discrimination distance between competing patterns. The highly confusable English E-set (b, c, d, e, g, p, t, v, z) is used to demonstrate the efficiency of the ASTNN. We show that the recognition rate can reach 80% for single-speaker and 68% for multispeaker respectively. | en_US |
| dc.language.iso | en | en_US |
| dc.publisher | IEEE | en_US |
| dc.title | Adaptive spatiotemporal neural network for speech recognition | en_US |
| dc.type | conference paper | en_US |
| dc.relation.conference | Proceedings of ICNN'95 - International Conference on Neural Networks | en_US |
| dc.relation.conference | Perth, WA, Australia | en_US |
| dc.identifier.doi | 10.1109/ICNN.1995.488191 | - |
| item.openairecristype | http://purl.org/coar/resource_type/c_5794 | - |
| item.cerifentitytype | Publications | - |
| item.languageiso639-1 | en | - |
| item.fulltext | no fulltext | - |
| item.grantfulltext | none | - |
| item.openairetype | conference paper | - |
| crisitem.author.dept | College of Electrical Engineering and Computer Science | - |
| crisitem.author.dept | Department of Electrical Engineering | - |
| crisitem.author.dept | National Taiwan Ocean University,NTOU | - |
| crisitem.author.parentorg | National Taiwan Ocean University,NTOU | - |
| crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
| Appears in Collections: | 電機工程學系 | |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.