首页 | 本学科首页   官方微博 | 高级检索  
     

基于DSP的语音识别系统设计
引用本文:李俊,周海滨,邱胜林,张艳珍,蔡晓燕.基于DSP的语音识别系统设计[J].适用技术之窗,2011(7):118-122.
作者姓名:李俊  周海滨  邱胜林  张艳珍  蔡晓燕
作者单位:江西财经大学软件与通信工程学院,江西南昌330013
摘    要:系统以16位数字信号处理器TMS320VC5502为核心,采用音频Codec芯片TLV320AIC23对语音信号进行采集和编码转换,通过端点检测、特征参数提取、DTW算法等关键技术实现特定人、小词汇量、孤立词的语音识别,最终根据LED闪灯次数检测数字0~9的识别结果。

关 键 词:语音识别  TMS320VC5502  TLV320AIC23  DTW算法

Design of Speech Recognition System Based on DSP
Li Jun Zhou Haibin Qiu Shenglin Zhang Yanzhen Cai Xiaoyan.Design of Speech Recognition System Based on DSP[J].Science & Technology Plaza,2011(7):118-122.
Authors:Li Jun Zhou Haibin Qiu Shenglin Zhang Yanzhen Cai Xiaoyan
Affiliation:Li Jun Zhou Haibin Qiu Shenglin Zhang Yanzhen Cai Xiaoyan (College of Software & Communication Engineering, Jiangxi University of Finance and Economics, Jiangxi Nanchang 330013)
Abstract:The system based on the 16-bit digital signal processor TMS320VC5502, using audio codec TLV320AIC23 to acquire and transcoding the voice signal, achieving a speaker dependent and small vocabulary isolated word speech recognition by endpoint detection, characteristic parameters extraction, DTW algorithm and other key technologies, ultimately according to the flash frequency of LED to detect recognition results from numbers 0 to 9.
Keywords:Speech Recognition  TMS320VC5502  TLV320AIC23  DTW Algorithm
本文献已被 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号