酒店服务机器人语音交互系统设计  

Design of Speech Interaction System on Hotel Service-robot

作　　者：周君 刘璟[1] ZHOU Jun;LIU Jing(School of Instrument Science and Engineering,Southeast University,Nanjing 210096,China)

机构地区：[1]东南大学仪器科学与工程学院,南京210096

出　　处：《软件导刊》2018年第11期13-16,21,共5页Software Guide

基　　金：江苏省普通高校研究生科研创新计划项目(2016);中央高校基本科研业务费专项资金项目(2016);东南大学基本科研业务费项目(SJLX16_0075)

摘　　要：为了使服务机器人在酒店管理中发挥更大作用,节省酒店成本,基于运行Android系统的友善之臂Tiny4412平台,设计了一款面向酒店服务机器人的错误率低、实时性高的语音交互系统,系统包括人脸检测、语音合成、语义理解和语法识别等部分。通过移植OpenCV库到Android系统中,利用OpenCV库中AdaBoost算法实现实时人脸检测;通过网络连接科大讯飞的讯飞开放平台获得海量语音资源,实现语音交互系统的语音识别、语义理解和语法识别功能;通过Tiny4412串口向下位机传输数据,实现对下位机运动控制。实践测试表明,系统可以检测到酒店客人到来、回答客人关于酒店的基本问题、完成基本引领工作,使机器人提供更好的服务。Based on the friendly arm board Tiny4412 with Android system,this paper studied the speech interaction system with low error rate and high real-time performance on the hotel service-robot in order to make the service-robot play a greater role in hotel management and save costs.The system includes face detection,speech synthesis,speech understanding,speech recognition and so on.OpenCV is ported to the Android platform.The AdaBoost algorithm is used to achieve real-time face detection combined with the OpenCV library.The system obtains a large amount of voice resources and achieves speech recognition,speech understanding,speech recognition through the network connection to the cloud platform of IFLYTEK.Speech recognition is applied to the motion control of the lower machine Tiny4412's serial port to transmit data.The system can detect the arrival of hotel guests,answer basic questions about the hotel and complete the basic guidance so that better service is provided.

关 键 词：语音交互 ANDROID 酒店机器人 人脸检测 Tiny4412 

分 类 号：TP302[自动化与计算机技术—计算机系统结构]