Accent-Voice Power via Audio wave Process Dr. Dhaval A Jadhav In charge Principal, Department of Computer Science, Vidyabharti Trust College of MCA , Umrakh-Bardoli, Dist.Surat,(Gujarat), INDIA jadhavdhaval@gmail.com Abstract On the voice development platform of Microsoft Speech SDK, speech recognition and speech synthesis modules based on command control mode is built in this paper. Ethernet-based remote voice control system of intelligent flexible manufacturing cell is developed for machine tools and industrial robots. This paper designs an intelligent voice control system based on LabVIEW development environment, which realizes the human-machine voice interaction of flexible manufacturing cell and remote voice control. Audio signal processing is also designed in this paper based on MATLAB platform, which largely reduces the effects caused by environmental noises. The mixing programming of LABVIEW and MATLAB can realize audio signal acquisition and processing easily and finally achieve reliable speech recognition system. Experimental studies have shown that intelligent voice control system has high speech recognition rate and system reliability both in quiet and adverse environments. Keywords: Audio Signal, Speech Recognition, Microsoft Speech SDK, Voice Control 1. Introduction Speech recognition is a high technology to make machines convert voice signals into appropriate texts or commands through recognition and understanding of the process. At present, Microsoft provides mature voice technology worldwide and has speech engine and corresponding development kit. Microsoft Speech API is a component object model (COM) and offers object programming interface, so it can be applied to any language that supports COM technology. SAPI (speech application programming interface) provides researchers with a large number of interfaces for speech recognition and speech synthesis secondary development, which can save system development time. As a result, Microsoft Speech SDK (software development kit) has broad applications [1]. In addition, Microsoft has also developed system speech recognition based on .net class library, which has the main achievement of Windows desktop operating speech recognition. It can also be able to realize simple voice secondary development based on the Windows API of WIN7 system. For the unsatisfactory results of speech recognition system based on Microsoft Speech SDK in noisy GEDRAG & ORGANISATIE REVIEW - ISSN:0921-5077 VOLUME 33 : ISSUE 02 - 2020 http://lemma-tijdschriften.nl/ Page No:1695