SYSTEMS AND METHODS FOR SPEECH-TO-SPEECH TRANSLATI

专利名称：SYSTEMS AND METHODS FOR SPEECH-TO-SPEECH TRANSLATION

发明人：Justin R. Kent申请号：US13151996申请日：20110602

公开号：US20110238407A1公开日：20110929

专利附图：

摘要：Disclosed herein are systems and methods for receiving an input speech samplein a first language and outputting a translated speech sample in a second language in theunique voice of a user. According to several embodiments, a translation system includes a

training mode for developing a voice recognition database and a user phonetic dictionary.A speech recognition module uses a voice recognition database to recognize andtranscribe the input speech samples in a first language. Subsequently, the text in the firstlanguage is translated to text in a second language, and a speech synthesizer developsan output speech in the unique voice of the user utilizing a user phonetic dictionary. Theuser phonetic dictionary may contain basic sound units, including phones, diphones,triphones, and/or words. Additionally, a translator may employ an N-gram statisticalmodel, Markov Models, and/or smoothing algorithms.

申请人：Justin R. Kent

地址：Mission TX US

国籍：US

更多信息请下载全文后查看