%0 Journal Article
%T An Appropriate Parallel HMM for Speaker-Independent Speech Recognition<br>一种适于非特定人语音识别的并行隐马尔可夫模型
%A Chen Yan-xiang
%A Dai Bei-qian
%A Zhou Xi
%A Liu Ming
%A <br>陈雁翔
%A 戴蓓蒨
%A 周曦
%A 刘鸣
%J 电子与信息学报
%D 2004
%I 
%X In this paper Parallel Hidden Markov Model(PHMM)made up of several parallel Markov chains is proposed to fit in with speaker-independent speech recognition. The performance is improved because of the fusion of different models from classification based speech recognition. By sharing states of fused models, making classification automatically during training and getting result from all classifications, the amount of storage and operation can be decreased. The experiment for speaker-independent recognition of mandarin isolated digit shows that the PHMM improves the recognition performance and noise robustness.
%K Speaker-independent speech recognition
%K Continuous Hidden Markov Model(CHMM)
%K Parallel Markov chain<br>非特定人语音识别
%K 连续隐马尔可夫模型
%K 并行马尔可夫链
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=1319827C0C74AAE8D654BEA21B7F54D3&jid=EFC0377B03BD8D0EF4BBB548AC5F739A&aid=D1C473C1B198FE7A&yid=D0E58B75BFD8E51C&vid=96C778EE049EE47D&iid=F3090AE9B60B7ED1&sid=D5BC5BD8C68CDE3A&eid=C20D616EFC5754AE&journal_id=1009-5896&journal_name=电子与信息学报&referenced_num=2&reference_num=3