Word recognition based on the combination of a sequential neural network and the GPDM discriminative training algorithm

Wen Yuan Chen*, Sin-Horng Chen

*Corresponding author for this work

研究成果: Conference contribution

3 引文 斯高帕斯(Scopus)

摘要

The authors propose an isolated-word recognition method based on the combination of a sequential neural network and a discriminative training algorithm using the Generalized Probabilistic Descent Method (GPDM). The sequential neural network deals with the temporal variation of speech by dynamic programming, and the GPDM discriminative training algorithm is used to discriminate easily confused words by enhancing the distinguishing sounds of them during the scoring procedure. A Mandarin digit database uttered by 100 speakers was used to evaluate the performance of this method. The recognition rates are 99.1% on training data and 96.3% on testing data.

原文English
主出版物標題Neural Networks for Signal Processing
發行者Publ by IEEE
頁面376-384
頁數9
ISBN(列印)0780301188
DOIs
出版狀態Published - 1 六月 1991
事件Proceedings of the 1991 Workshop on Neural Networks for Signal Processing - NNSP-91 - Princeton, NJ, USA
持續時間: 30 九月 19912 十月 1991

出版系列

名字Neural Networks for Signal Processing

Conference

ConferenceProceedings of the 1991 Workshop on Neural Networks for Signal Processing - NNSP-91
城市Princeton, NJ, USA
期間30/09/912/10/91

指紋 深入研究「Word recognition based on the combination of a sequential neural network and the GPDM discriminative training algorithm」主題。共同形成了獨特的指紋。

引用此