Isolated word recognition using neural networks
This paper presents the speech recognition system, designed for recognition of 50 isolated Lithuanian words. The system is based on feedforward neural networks trained by error backpropagation algorithm. Speaker dependent speech recognition was investigated. The article presents analysis of the dev...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Vilnius University Press
2003-12-01
|
| Series: | Lietuvos Matematikos Rinkinys |
| Online Access: | https://www.journals.vu.lt/LMR/article/view/32539 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832593142793109504 |
|---|---|
| author | Mark Filipovič |
| author_facet | Mark Filipovič |
| author_sort | Mark Filipovič |
| collection | DOAJ |
| description |
This paper presents the speech recognition system, designed for recognition of 50 isolated Lithuanian words. The system is based on feedforward neural networks trained by error backpropagation algorithm. Speaker dependent speech recognition was investigated. The article presents analysis of the developed system parameters influence on the accuracy of word recognition. Experimental results showed that proposed system could be used for isolated word recognition.
|
| format | Article |
| id | doaj-art-517ac730bcb444af868261b510ac4b73 |
| institution | Kabale University |
| issn | 0132-2818 2335-898X |
| language | English |
| publishDate | 2003-12-01 |
| publisher | Vilnius University Press |
| record_format | Article |
| series | Lietuvos Matematikos Rinkinys |
| spelling | doaj-art-517ac730bcb444af868261b510ac4b732025-01-20T18:17:23ZengVilnius University PressLietuvos Matematikos Rinkinys0132-28182335-898X2003-12-0143spec.10.15388/LMR.2003.32539Isolated word recognition using neural networksMark Filipovič0Institute of Mathematics and Informatics This paper presents the speech recognition system, designed for recognition of 50 isolated Lithuanian words. The system is based on feedforward neural networks trained by error backpropagation algorithm. Speaker dependent speech recognition was investigated. The article presents analysis of the developed system parameters influence on the accuracy of word recognition. Experimental results showed that proposed system could be used for isolated word recognition. https://www.journals.vu.lt/LMR/article/view/32539 |
| spellingShingle | Mark Filipovič Isolated word recognition using neural networks Lietuvos Matematikos Rinkinys |
| title | Isolated word recognition using neural networks |
| title_full | Isolated word recognition using neural networks |
| title_fullStr | Isolated word recognition using neural networks |
| title_full_unstemmed | Isolated word recognition using neural networks |
| title_short | Isolated word recognition using neural networks |
| title_sort | isolated word recognition using neural networks |
| url | https://www.journals.vu.lt/LMR/article/view/32539 |
| work_keys_str_mv | AT markfilipovic isolatedwordrecognitionusingneuralnetworks |