| 嵌入式语音控制系统在QT上的实现 |
| |
| 引用本文： | 肖方,施玉霞,李刚.嵌入式语音控制系统在QT上的实现[J].电声技术,2010,34(10):54-56,61. |
| |
| 作者姓名： | 肖方 施玉霞 李刚 |
| |
| 作者单位： | 1. 南京航空航天大学,自动化学院,江苏,南京,210016
2. 南京邮电大学,通信与信息工程学院,江苏,南京,210003 |
| |
| 摘 要： | 介绍了一款非特定人嵌入式语音控制系统。硬件平台采用mini2440开发板，其CPU处理器是三星公司的S3C2440：针对嵌入式系统存储空间有限和实时性要求高的特点．在特征提取后加入LBG算法以减少系统的存储量和计算量；识别阶段采用DHMM算法，计算量少，适应性强。将该系统用于语音对机械手臂的控制试验，结果表明本系统的识别率达到了98％以上，运算速度快，计算复杂度小，能满足一般应用对语音控制的需求，在市场上具有广泛的应用前景。
|
| 关 键 词： | 语音识别 离散隐马尔科夫模型 $3C2440处理器 梅尔频率倒谱系数 矢量量化 |
Implementation of Embedded Speech Control System Based on QT |
| |
| XIAO Fang,SHI Yuxia,LI Gang.Implementation of Embedded Speech Control System Based on QT[J].Audio Engineering,2010,34(10):54-56,61. |
| |
| Authors: | XIAO Fang SHI Yuxia LI Gang |
| |
| Institution: | XIAO Fang1,SHI Yuxia1,LI Gang2 (1. Department of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China,2. Department of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China) |
| |
| Abstract: | A speaker independent embedded speech system is introduced. The hardware platform is mini2440 development board using S3C2440 microprocessors; the storage space is limited and real-time is demanded highly in embedded system. In order to resolve the problems, LBG algorithm is applied after feature extraction to reduce storage of system and calculation, and HMM algorithm is used in recognition, less computational effort and strong adaptability. The speech recognition accuracy reaches up 98% when using the sys... |
| |
| Keywords: | speech recognition DHMM S3C2440 MFCC vector quantization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
