Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/44292
標題: Dynamic programming prediction errors of recurrent neural fuzzy networks for speech recognition
作者: Juang, C.F.
莊家峰
Lai, C.L.
Tu, C.C.
關鍵字: Phrase recognition
Recurrent fuzzy systems
Fuzzy neural networks
Recurrent neural fuzzy networks
Noisy speech recognition
hidden markov-models
systems
noise
identification
adaptation
algorithm
期刊/報告no:: Expert Systems with Applications, Volume 36, Issue 3, Page(s) 6368-6374.
摘要: This paper proposes Mandarin phrase recognition using dynamic programming (DP) prediction errors of singleton-type recurrent neural fuzzy networks (SRNFNs). This method is called DP-SRNFN. The recurrent property of SRNFN makes it suitable for processing temporal speech patterns. A Mandarin phrase comprises monosyllabic words. SRNFN training is based on the word unit. There are N(w) SRNFNs for modeling Nw words, and each SRNFN receives the current frame feature and predicts the next one of its modeling word. In recognizing N(P) phrases, the prediction error of each trained SRNFN is computed, and DP is used to find the optimal path that maps the input frames to the best matched SRNFNs (words) for each of the N(P) phrases. The accumulated error of each phrase model is computed from its optimal path and the one with the minimum error is the recognition result. To verify DP-SRNFN performance, this study conducted experiments on recognizing 30 Mandarin phrases. SRNFN training with noisy features for phrase recognition under different noisy environments was also conducted. DP-SRNFN performance is compared with the hidden Markov models (HMMs). Results show that DP-SRNFN achieves higher recognition rates than HMM in both clean and noisy environments. (C) 2008 Elsevier Ltd. All rights reserved.
URI: http://hdl.handle.net/11455/44292
ISSN: 0957-4174
文章連結: http://dx.doi.org/10.1016/j.eswa.2008.07.061
Appears in Collections:電機工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.