Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/99324
DC Field | Value | |
---|---|---|
dc.title | Large vocabulary Mandarin Final recognition based on Two-Level Time-Delay Neural Networks (TLTDNN) | |
dc.contributor.author | Poo, G.-S. | |
dc.date.accessioned | 2014-10-27T06:02:56Z | |
dc.date.available | 2014-10-27T06:02:56Z | |
dc.date.issued | 1997-07 | |
dc.identifier.citation | Poo, G.-S. (1997-07). Large vocabulary Mandarin Final recognition based on Two-Level Time-Delay Neural Networks (TLTDNN). Speech Communication 22 (1) : 17-24. ScholarBank@NUS Repository. | |
dc.identifier.issn | 01676393 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/99324 | |
dc.description.abstract | A Two-Level Time-Delay Neural Network (TLTDNN) technique has been developed to recognize all Mandarin Finals of the entire Chinese syllables. The first level discriminates the vowel-group based on (a, e, i, o, u, v) and the nasal-group based on nasal ending (-n, -ng, -others). The nasal-group discriminator is used to further split the large /a/ subgroup produced by the vowel-group discriminator. The two groupings in the first level produce 8 subgroups in the second level. Further discrimination in the second level enables the identification of all 35 Mandarin Finals. The technique was thoroughly tested using 8 sets of 1265 isolated Hanyu Pinyin syllables, with 6 sets used for training and 2 sets used for testing. The overall result shows that a high recognition rate of 99.4% on the training datasets and 95.6% on the test datasets, is achievable. The top 4 recognition rate attained on the test datasets is as high as 99.1%. © 1997 Elsevier Science B.V. | |
dc.source | Scopus | |
dc.subject | Mandarin finals | |
dc.subject | Speech recognition | |
dc.subject | Time-Delay Neural Network (TDNN) | |
dc.type | Article | |
dc.contributor.department | INFORMATION SYSTEMS & COMPUTER SCIENCE | |
dc.description.sourcetitle | Speech Communication | |
dc.description.volume | 22 | |
dc.description.issue | 1 | |
dc.description.page | 17-24 | |
dc.description.coden | SCOMD | |
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.
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.