首页> 外文会议>International Speech Communication Association >Silence Models in Weighted Finite-State Transducers
【24h】

Silence Models in Weighted Finite-State Transducers

机译:加权有限状态换能器中的沉默模型

获取原文

摘要

We investigate the effects of different silence modelling strategies in Weighted Finite-State Transducers for Automatic Speech Recognition. We show that the choice of silence mod-els, and the way they are included in the transducer, can have a significant effect on the size of the resulting transducer; we present a means to prevent particularly large silence overheads. Our conclusions include that context-free silence modelling fits well with transducer based grammars, whereas modelling silence as a monophone and a context has larger overheads.
机译:我们调查不同沉默建模策略在加权有限状态传感器中的自动语音识别的影响。我们表明,沉默的选择模式,以及它们包括在换能器中的方式,可以对所得换能器的尺寸产生显着影响;我们展示了一种防止特别大的沉默的手段。我们的结论包括与基于换能器的语法非常适合无与伦比的沉默建模,而将沉默作为单声道建模,并且上下文具有更大的开销。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号