首页> 外文会议> >A method for automatic extraction of F/sub 0/ contour generation process model parameters for Mandarin
【24h】

A method for automatic extraction of F/sub 0/ contour generation process model parameters for Mandarin

机译:自动提取普通话F / sub 0 /轮廓生成过程模型参数的方法

获取原文

摘要

The model of F/sub 0/ contour generation has been successfully applied to Mandarin, which is a typical tone language with a distinct feature that both positive and negative tone commands are required. In this paper, a method is proposed for automatic extraction of parameters of the F/sub 0/ contour model for Mandarin. With the same framework as that proposed for Japanese and English, the method presented here for Mandarin is focused on the first-order estimation of tone command parameters. In order to distinguish between positive and negative tone commands, the information on syllable timing and tone labels is employed, and a set of rules are constructed to recognize the tone command patterns within each syllable. A preliminary experiment indicates that the method works effectively and gives results comparable with those obtained by manual analysis.
机译:F / sub 0 /等高线生成模型已成功应用于普通话,普通话是一种典型的音调语言,具有明显的特征,即需要正负两个音调命令。本文提出了一种自动提取普通话F / sub 0 /轮廓模型参数的方法。在与针对日语和英语提出的框架相同的情况下,此处针对普通话提出的方法侧重于音调命令参数的一阶估计。为了区分正和负音调命令,使用了有关音节定时和音调标签的信息,并且构造了一组规则以识别每个音节内的音调命令模式。初步实验表明,该方法行之有效,其结果可与通过手动分析获得的结果相媲美。

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