Gain Adaptive Nonlinear Quantization Based on BP Neural Network

机译：基于BP神经网络的增益自适应非线性量化。

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

This paper analyzes the limitation of fixed gain quantization in G.728 speech coding algorithm, and proposes an adaptive quantization scheme with exact gain. Then, BP neural network is used to quantize nonlinearly the exact gain of G.728. Because BP neural network is of the nonlinear mapping ability, it is used in this quantization method, which is well trained through many examples learning. The experimental results show: the average segment SNR (signal noise rate) of gain is increased by 1dB, the SNR of sentences is by 0.4dB than traditional one, and gain's by 3dB, sentence's by about 2dB than that of G.728.

机译：分析了G.728语音编码算法中固定增益量化的局限性，提出了一种具有精确增益的自适应量化方案。然后，使用BP神经网络对G.728的精确增益进行非线性量化。由于BP神经网络具有非线性映射功能，因此在此量化方法中使用了BP神经网络，并通过许多实例学习对其进行了很好的训练。实验结果表明：增益的平均分段SNR（信号噪声速率）比传统的提高了1dB，句子的SNR比传统的提高了0.4dB，增益比G.728的提高了3dB，句子提高了约2dB。

著录项

来源
《Sixth International Conference on Electronic Measurement amp; Instruments (ICEMI '2003) Vol.1; Aug 18-21, 2003; Taiyuan, China》|2003年|p.373-376|共4页
会议地点 Taiyuan(CN);Taiyuan(CN)
作者
Yan Lirui; Zhang Xueying; Zhang Gang;
展开▼
作者单位

Information Engineering College, Taiyuan University of Technology, Taiyuan, Shanxi, 030024,China;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类机械、仪表工业;
关键词
adaptive; nonlinear; neural;

机译：自适应;非线性;神经;

相似文献

外文文献
中文文献
专利

1. Neural-networks-based adaptive quantized feedback tracking of uncertain nonlinear strict-feedback systems with unknown time delays [J] . Choi Yun Ho, Yoo Sung Jin Journal of the Franklin Institute . 2020,第15期

机译：基于神经网络的自适应量化反馈跟踪，不确定的非线性严格反馈系统，具有未知的时间延迟
2. Neural-network-based distributed adaptive asymptotically consensus tracking control for nonlinear multiagent systems with input quantization and actuator faults [J] . Li Yu, Wang Chaoli, Cai Xuan, Neurocomputing . 2019,第JULa15期

机译：输入量化和执行器故障的非线性多智能体系统基于神经网络的分布式自适应渐近共识跟踪控制
3. Neural-network-based distributed adaptive asymptotically consensus tracking control for nonlinear multiagent systems with input quantization and actuator faults [J] . Li Yu, Wang Chaoli, Cai Xuan, Neurocomputing . 2019,第Jul15期

机译：基于神经网络的基于网络的分布式自适应渐近渐近渐近渐近渐近与输入量化和执行器故障的非线性多算系统的分布式渐近兼容性兼容性跟踪控制
4. Gain Adaptive Nonlinear Quantization Based on BP Neural Network [C] . Yan Lirui, Zhang Xueying, Zhang Gang International Conference on Electronic Measurement Instruments . 2003

机译：基于BP神经网络获得自适应非线性量化
5. Orthonormal activation function-based neural networks for adaptive control of nonlinear systems. [D] . Shukla, Deepak. 1996

机译：基于正交激活函数的神经网络，用于非线性系统的自适应控制。
6. A Highly Linear CMOS Image Sensor Design Based on an Adaptive Nonlinear Ramp Generator and Fully Differential Pipeline Sampling Quantization with a Double Auto-Zeroing Technique [O] . Chuangze Li, Benguang Han, Jie He, 2020

机译：基于自适应非线性斜坡发生器和双差分自动归零技术的全差分流水线采样量化的高度线性CMOS图像传感器设计
7. The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization [O] . Wielgosz, Maciej, Mertik, Matej, Skoczeń, Andrzej, 2017

机译：基于Dsp的HiLumi LHC磁体异常检测器模型递归神经网络和自适应量化

Gain Adaptive Nonlinear Quantization Based on BP Neural Network

摘要

著录项

相似文献

相关主题

期刊订阅