首页> 外国专利> Method for optimizing synthesized speech, method for generating speech synthesis filter, speech optimization method, and speech optimization device

Method for optimizing synthesized speech, method for generating speech synthesis filter, speech optimization method, and speech optimization device

机译:用于优化合成语音的方法,用于生成语音合成滤波器的方法,语音优化方法和语音优化装置

摘要

An optimization algorithm is provided for linear prediction based speech coding systems. The optimization algorithm minimizes the error (I) between original speech samples and synthesized speech samples. Optimized linear prediction coefficients (a1, ..., aM) are computed directly from a system difference equation without converting the coefficients into the root-domain. IMAGE
机译:为基于线性预测的语音编码系统提供了一种优化算法。优化算法使原始语音样本和合成语音样本之间的误差(I)最小化。从系统差分方程直接计算优化的线性预测系数(a1,...,aM),而无需将系数转换为根域。 <图像>

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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