Speech recognition system and speech recognition m

专利名称：Speech recognition system and speech

recognition method

发明人：Chang Heon Lee,Kyuseop Bang申请号：US14745645申请日：20150622公开号：US09286888B1公开日：20160315

专利附图：

摘要：A speech recognition system includes: a context storage medium storing amonosyllabic command context including a plurality of monosyllabic commands andstoring a polysyllabic command context including a plurality of polysyllabic commands; a

speech segment detector detecting a speech segment having a start point and an endpoint by analyzing a speech signal within the speech segment; a syllable determinerconfigured determining whether the speech signal corresponds to a monosyllabic formor a polysyllabic form; a feature vector extractor extracting a feature vector by analyzingthe speech signal; and a speech recognizer selecting one of the monosyllabic commandcontext and the polysyllabic command context according to the determination ofwhether the speech signal corresponds to the monosyllabic form or the polysyllabicform and recognizing at least one command in the selected one of the monosyllabiccommand context and the polysyllabic command context based on the extracted featurevector.

申请人：Hyundai Motor Company

地址：Seoul KR

国籍：KR

代理机构：Mintz Levin Cohn Ferris Glovsky and Popeo, P.C.

代理人：Peter F. Corless

更多信息请下载全文后查看