Speech recognition using middle-to-middle context hidden markov models
    1.
    发明授权
    Speech recognition using middle-to-middle context hidden markov models 失效
    使用中 - 中间上下文隐马尔可夫模型的语音识别

    公开(公告)号:US5812974A

    公开(公告)日:1998-09-22

    申请号:US631731

    申请日:1996-04-10

    摘要: This is a speech recognition method for modeling adjacent word context, comprising: dividing a first word or period of silence into two portions; dividing a second word or period of silence, adjacent to the first word, into two potions; and combining last portion of the first word or period of silence and first portion of the second word or period of silence to make an acoustic model. The method includes constructing a grammar to restrict the acoustic models to the middle-to-middle context.

    摘要翻译: 这是一种用于建模相邻字词上下文的语音识别方法,包括:将第一个单词或一段静音划分成两部分; 将与第一个单词相邻的第二个单词或沉默时期分成两个部分; 并且将第一个单词的最后部分或者第二个单词的静默阶段和第一个单词的静默周期组合起来,以形成声学模型。 该方法包括构建一个语法,将声学模型限制到中间到中上下文。