| 一种基于回归神经网络的码本激励非线性预测话音编码算法 |
| |
| 引用本文： | 马霓,韦岗.一种基于回归神经网络的码本激励非线性预测话音编码算法[J].通信学报,2000,21(10):31-37. |
| |
| 作者姓名： | 马霓 韦岗 |
| |
| 作者单位： | 1. 华南理工大学电子信息学院,广东,广州,510640;广州金鹏集团有限公司,广东,广州,510665
2. 华南理工大学电子与通信工程系,广东,广州,510640 |
| |
| 基金项目： | 国家自然科学基金资助项目 !( 6960 2 0 0 2，69772 0 2 7)，广东省自然科学基金资助项目!( 960 2 2 7，963 0 3 7) |
| |
| 摘 要： | 为改善预测类声码器中长时预测器特性，本文引入了一种全连接回归神经网络（ＦＲＮＮ）非线性预测器并将其应用于话音编码算法中。ＦＲＮＮ在隐层单元不仅有来自自身的反馈，也有来自输出单元的反馈，因此其预测性能好于常规预测器。将其应用于码本激励话音编码系统（ＣＥＬＰ）中，可得到较低的传输码率，同时亦可改善编码质量。
|
| 关 键 词： | 非线性预测 回归神经网络 话音编码 码本激励 |
| 修稿时间： | 2000-02-15 |
A code-excited nonlinear predictive speech coding algorithm based on recurrent neural networks |
| |
| MA Ni,WEI Gang.A code-excited nonlinear predictive speech coding algorithm based on recurrent neural networks[J].Journal on Communications,2000,21(10):31-37. |
| |
| Authors: | MA Ni WEI Gang |
| |
| Abstract: | To improve the long term correlation prediction characteristics in speech coding,this paper propose a new nonlinear predictor,i e ,a fully connected recurrent neural network(FRNN) where the hidden units have feedbacks not only from themselves but also from the output unit The comparison of the capabilities of the FRNN with conventional predictors shows that the former has less prediction error than the latter We apply this FRNN in the code excited predictive speech coding system(CELP) and shows that the FRNN requires less bit rate and improves the performance for speech coding |
| |
| Keywords: | nonlinear prediction fully connected recurrent neural networks vector quantization speech coding |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
