Donetsk National Technical University
Please use this identifier to cite or link to this item:
https://ea.donntu.edu.ua/jspui/handle/123456789/15912| Title: | МНОГОУРОВНЕВАЯ НЕЙРОСЕТЕВАЯ СТРУКТУРА РАСПОЗНАВАНИЯ РЕЧЕВЫХ СЛОВ ПО НИЗКОЧАСТОТНЫМ ГАРМОНИКАМ |
| Other Titles: | Neural structure with many layers to recognize of speech words by low-frequency harmonics |
| Authors: | Федяев, О.И. Гладунов, С.А. Fedyaev, O.I. Gladunov, S. A |
| Keywords: | recognition process modeling Многоуровневая нейросетевая структура Multilevel neyrosetevaya structure nizkochastotnaya accordion низкочастотная гармоника речевые слова |
| Issue Date: | 2002 |
| Publisher: | ДонНТУ |
| Citation: | Наукові праці Донецького національного технічного університету, серія «Інформатика, кібернетика та обчислювальна техніка»,випуск 39, Донецк, ДонНТУ, 2002 |
| Description: | In this work it was proposed a method of an isolated words recognition based on a decomposition of spectral pattern. It was designed a two-layer scheme of recognition based on an integral estimation of belonging harmonics of words and it's realization in a neural network basis. There are results described of a recognition process modeling. |
| URI: | http://ea.donntu.edu.ua/handle/123456789/15912 |
| Appears in Collections: | Випуск 39 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.