Intelligent robotic system for home services speech recognition and synthesizing

• Main Author: Wang, Cun Zhe
• Other Authors: Er Meng Joo
• Format: Final Year Project
• Language: English
• Published: 2010
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics
• Online Access: http://hdl.handle.net/10356/40795
• Institution: Nanyang Technological University

In the last few decades, robot technologies have been rapidly developed for various uses, such as industry automation, surgical robots, military and exploration. The entertainment and service robotic have also become well known since some manufactures were able to show humanoid robots dancing. This project aims to design and fabricate a home service robot in five fields that are Speech Recognition and Synthesizer, Robot Vision System, Robot Arm Manipulation, Mechanism Design and Control, and Robot Mapping System. Therefore, firstly this report will discuss the direction of home service robotic development and reasons of the five researching fields which are carried out. Secondly, an automated voice recognition and speech for home service robot is proposed in the Speech Recognition and Synthesizer part. To achieve the purpose, Microsoft speech engine was used to build the robot‘s discourse ability system. Microsoft Visual Basic.Net was used as a software developing tool in the speech recognition and synthesizer. A Visual Basic.Net programming was developed that is not only achieved speech conversation between robot and operator, but also associated various Microsoft applications, like PowerPoint and Internet Explorer. The Microsoft Office involved makes the robot functional in office. Finally, a speech classifier should be adaptive to different users and robust to noisy environment. At a domestic environment, the background noise is a major issue in speech recognition accuracy. Therefore, a basic signal processing was simulated using Matlab for the background noise cancellation research. The first step simulation results provide a ground work for future design of the background noise filter algorithms.