Recognition of Speech Based on HMM/MLP Hybrid Network  

基于HMM/MLP混合网络模型的语音识别方法(英文)

作　　者：黄心晔[1] 马小辉[1] 李想[1] 富煜清[1] 陆佶人[1] 

机构地区：[1]东南大学无线电工程系,南京210096

出　　处：《Journal of Southeast University(English Edition)》2000年第2期26-30,共5页东南大学学报（英文版）

基　　金：TheprojectsupportedbytheNationalNatureScienceFoundationofChina! (6 96 72 0 10 )

摘　　要：This paper presents a new HMM/MLP hybrid network for speech recognition. By taking advantage of the discriminative training of MLP, the unreasonable model correctness assumption on the model correctness of the ML training in basic HMM can be overcome, and its discriminative ability and recognition performance can be improved. Experimental results demonstrate that the discriminative ability and recognition performance of HMM/MLP is apparently better than normal HMM.提出了一种新的用于语音识别的HMM MLP混合网络 ,它利用MLP的鉴别训练能力 ,以克服基本HMM的ML训练方法中不合理的模型正确性假设前提 ,提高HMM的鉴别能力和识别性能 .实验结果证明HMM MLP混合网络的鉴别能力和识别性能明显高于普通HMM .

关 键 词：HMM/MLP hybrid network discriminative training speech recognition 

分 类 号：TN912.34[电子电信—通信与信息系统]