【24h】

A non-linear prediction speech coding system based on ANN

机译:基于人工神经网络的非线性预测语音编码系统

获取原文

摘要

A non-linear prediction speech coding system based on an ANN is introduced. In this coding system, the bit rate is not increased by the backward predictor. The pure backpropagation (BP) algorithm is replaced by the improved difference BP algorithm. The experimental results have indicated: the predictor based on an ANN has high prediction gain and the speech dependencies can been extracted by it though the embedding dimension is low. The speed quality of the new system is better than that of the speech coding standard G.721 system.
机译:介绍了一种基于人工神经网络的非线性预测语音编码系统。在该编码系统中,后向预测器不增加比特率。纯反向传播(BP)算法被改进的差分BP算法取代。实验结果表明:尽管嵌入维数较低,但基于人工神经网络的预测器具有较高的预测增益,可以提取语音依存关系。新系统的速度质量优于语音编码标准G.721系统。

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