Please use this identifier to cite or link to this item:
|標題:||Hierarchical singleton-type recurrent neural fuzzy networks for noisy speech recognition||作者:||Juang, C.F.
|關鍵字:||hierarchical networks;neural filters;neural fuzzy networks;noisy;speech filtering;recurrent neural networks;systems;identification;algorithms||Project:||Ieee Transactions on Neural Networks||期刊/報告no：:||Ieee Transactions on Neural Networks, Volume 18, Issue 3, Page(s) 833-843.||摘要:||
This paper proposes noisy speech recognition using hierarchical singleton-type recurrent neural fuzzy networks (HSRNFNs). The proposed HSRNFN is a hierarchical connection of two singleton-type recurrent neural fuzzy networks (SRNFNs), where one is used for noise filtering and the other for recognition. The SRNFN is constructed by recurrent fuzzy if-then rules with fuzzy singletons in the consequences, and their recurrent properties make them suitable for processing speech patterns with temporal characteristics. Inn, words recognition, 77, SRNFNs are created for modeling n words, where each SRNFN receives the current frame feature and predicts the next one of its modeling word. The prediction error of each SRNFN is used as recognition criterion. In filtering, one SRNFN is created, and each SRNFN recognizer is connected to the same SRNFN filter, which filters noisy speech patterns in the feature domain before feeding them to the SRNFN recognizer. Experiments with Mandarin word recognition under different types of noise are performed. Other recognizers, including multilayer perceptron (MLP), time-delay neural networks (TDNNs), and hidden Markov models (HMMs), are also tested and compared. These experiments and comparisons demonstrate good results with HSRNFN for noisy speech recognition tasks.
|Appears in Collections:||電機工程學系所|
Show full item record
TAIR Related Article
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.