基于BP和ARM的发动机声音识别系统  

Voice recognition engine based on BP's system in realization of ARM

作　　者：姜愉[1] 

机构地区：[1]钦州学院数学与计算机科学学院,广西钦州535000

出　　处：《黑龙江科技学院学报》2012年第5期533-536,共4页Journal of Heilongjiang Institute of Science and Technology

摘　　要：为解决高速公路收费站及大型停车收费场自动收费问题,依据BP神经网络识别理论,设计了一个基于ARM9及嵌入式Linux系统的发动机声音识别系统。选用S3C2410微处理器和嵌入式Linux操作系统,把交叉编译后的发动机声音识别C语言程序移植到操作系统的文件中,实现了发动机声音实时识别功能,给出了系统整体软硬件结构框架以及实时输入发动机声音判别汽车类型的识别结果。现场实验证实了该系统的准确性、实时性和有效性。Aimed at addressing automatic fee charging of highway toll stations and large-scale re- chargeable parking lots, this paper introduces the design of a embedded speech recognition system based on ARM9 and embedded Linux system of the engine sound by analyzing the BP neural network recognition theory. The design consisting of S3C2410 microprocessors and Linux operating systems involves trans- planting the C language of speech recognition program to the embedded Linux operating system＇s file system when cross-compiled. The paper describes the system s hardware and software framework, and offers the experiments results produced by real-time recognition of the car type by the engine sound. The results prove its accuracy, real-time and validity.

关 键 词：BP 嵌入式系统 S3C2410处理器 发动机声音 识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]