Title :
Study on recognition of speech based on HMM/MLP hybrid network
Author :
Xinye, Huang ; Xiaohui, Ma ; Xiang, Li ; Fu Yuqing ; Jiren, Lu
Author_Institution :
Dept. of Radio Eng., Southeast Univ., Nanjing, China
Abstract :
This paper presents a new HMM/MLP hybrid network for speech recognition. By taking advantage of the discriminative training of MLPs, the unreasonable assumption on the model correctness of ML training in basic HMMs can be overcome, and the discriminative power and recognition performance can be improved. Experimental results demonstrate the efficiency of the HMM/MLP
Keywords :
hidden Markov models; learning (artificial intelligence); multilayer perceptrons; speech recognition; HMM/MLP hybrid network; ML training; discriminative training; hidden Markov model; multilayer perceptron; speech recognition; Electronic mail; Equations; Erbium; Error correction; Hidden Markov models; Multilayer perceptrons; Power system modeling; Probability density function; Speech recognition; Viterbi algorithm;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.891611
