標題: An RNN-based preclassification method for fast continuous Mandarin speech recognition
作者: Chen, SH
Liao, YF
Chiang, SM
Chang, SG
電信工程研究所
Institute of Communications Engineering
公開日期: 1-一月-1998
摘要: A novel recurrent neural network-based (RNN-based) front-end preclassification scheme for fast continuous Mandarin speech recognition is proposed in this paper, First, an RNN is employed to discriminate each input frame for the three broad classes of initial, final, and silence, A finite state machine (FSM) is then used to classify the input frame into four states including three stable states of Initial (I), Final (F), and Silence (S), and a Transient (T) state, The decision is made based on examining whether the RNN discriminates well between classes, We then restrict the search space for the three stable states in the following DP search to speed up the recognition process, Efficiency of the proposed scheme was examined by simulations in which we incorporate it with a hidden Markov model-based (HMM-based) continuous 411 Mandarin base-syllables recognizer, Experimental results showed that it can be used in conjunction with the beam search to greatly reduce the computational complexity of the HMM recognizer while keeping the recognition rate almost undegraded.
URI: http://dx.doi.org/10.1109/89.650315
http://hdl.handle.net/11536/54
ISSN: 1063-6676
DOI: 10.1109/89.650315
期刊: IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING
Volume: 6
Issue: 1
起始頁: 86
結束頁: 90
顯示於類別:期刊論文


文件中的檔案:

  1. 000071264800009.pdf