期刊文献+

基于BP网络和多抽样率处理的缺失音频信号恢复方法 被引量:2

Missing audio signal recovery approach based on BP neural network and multirate processing
下载PDF
导出
摘要 提出并设计了一种由多个BP网络和均匀DFT滤波器组构成的非平稳序列自适应预测器,用于缺失音频信号的恢复.通过改进样本处理方法和分别设计各个BP网络结构,达到较高的预测精度.采用多抽样率并行处理方式,减少了单个BP网络的数据处理量,提高了预测器恢复缺失的音频信号速度.仿真实验证明效果较好. A nonstationary sequence predictor for missing audio signal recovery is presented and designed. The predictor consists of a few BP networks and a uniform DFT filter bank. Through the improved method of sample processing and designing every BP network respectively, the predictor reaches a high precision comparatively. The multirate parallel processing reduces the data quantity processed by one BP network and increases the speed of missing audio signal recovery. Stimulation results show that this method is effective and efficient.
出处 《大连理工大学学报》 EI CAS CSCD 北大核心 2004年第5期729-732,共4页 Journal of Dalian University of Technology
关键词 多抽样率 音频信号 滤波器组 自适应预测器 DFT 并行处理 恢复方法 失音 样本处理 缺失 Acoustic signal processing Backpropagation Parallel processing systems
  • 相关文献

参考文献8

  • 1JAN G, DE GOOIJER J G, KULDEEP K. Some recent developments in non-linear time series modelling, testing, and forecasting [J]. Int J of Forecasting, 1992, 8:135-156.
  • 2HAYKIN S. Neural Networks: A Comprehensive Foundation [M]. Beijing: Tsinghua Univ Press, 2001.
  • 3YOSHIHARA I, NUMATA M, SUGAWARA K. Time series prediction model building with BP-like parameter optimization [A]. Proceedings of the Congress on Evolutionary Computation [C]. Washington: [s n], 1999.
  • 4CRONE S F. Training artificial neural networks for time series prediction using asymivietric cost functions [A]. Proceedings of the 9th International Conference on Neural Information Processing [C]. Germany: [s n], 2002. 2374-2380.
  • 5COCCHI G, UNCINI A. Subband neural networks prediction for on-line audio signal recovery [J]. IEEE Trans Neural Networks, 2002, 13(4): 867-876.
  • 6HAGAN M T, MENHAJ M B. Training feedforward networks with the Marquardt algorithm [J]. IEEE Trans Neural Networks, 1994,5(6): 989-993.
  • 7YANG Y G, CHO N I, LEE S U. On the performance analysis of the subband adaptive digital filter [A]. IEEE International Symposium on Circuits and Systems [C]. Chicago: [s n], 1993. 64-67.
  • 8UNICINI A, COCCHI G. Subband neural networks for noisy signal forecasting and missing data [A]. Proceedings of the International Joint Conference on Neural Networks [C]. Honolulu: [s n], 2002. 438-441.

共引文献1

同被引文献11

引证文献2

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部