基于DSP和FPGA的机器人声控系统设计与实现  

Robot Voice Control System Design and Implementation with DSP and FPGA

作　　者：刘京诚[1] 高海英[1] 廖志勇[1] 

机构地区：[1]重庆大学光电工程学院,重庆400044

出　　处：《现代电子技术》2006年第14期109-112,共4页Modern Electronics Technique

摘　　要：介绍了一种基于DSP和FPGA的机器人声控系统。在语音采集上,将DSP芯片TMS320C5509和音频芯片TLV320AIC23相结合进行语音的采集。在软件开发上,开发环境采用CCS 3.1,语音特征向量采用美尔频率倒谱系数,模式匹配和训练采用隐马尔可夫模型,实现了语音指令的识别。在动作控制上,采用FPGA作为机器人头部动作逻辑控制器,使机器人能够根据非特定人的语音命令做出规定的头部动作。A robot voice control system based on DSP and FPGA is introduced in this paper. In speech acquisition part,DSP chip TMS320C5509 and audio chip TLV320AIC23 is combined to acquire the speech. In software design, system developing environment is CCS 3.1 and speech characteristic vector is Mel frequency cepstrum coeficient. In addition, Mel frequency cepstrum coeficient is used for pattern matching and training. All these finish speech recognition. In action control part,FPGA is used as a logic unit controlled the actions of robot head, which can make the robot behave the regulated actions according to indefinite voice commands.

关 键 词：语音识别 DSP FPGA 机器人 美尔频率倒谱系数 隐马尔可夫模型 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]