Speech interactive agent system for car navigation using embedded ASR/TTS and DSR

Abstract

This paper presents an efficient speech interactive agent rendering smooth car navigation and Telematics scrvices. by employing embedded automatic speech recognition (eASR), distributed speech recognition (DSR) and cmbeddcd text-to-speech (eTTS) modulcs, all while enabling safe driving. A speech interactive agcnt is essentially a conversational tool providing command and control functions to drivers such as enabling navigation task, audiolvideo manipulation, and E-commerce services through natural voicclresponse interactions between user and interface. To cope with the multiplc random inputs from mute buttons, hands-free buttons, push-to-talk buttons and events occurred by service applications on car navigation system, this provides resource ncgotiation rulcs using priority control based on inter-process communication, speech intcractivc helper function, multi-thread process and cxception handling. In addition, involved hardware resources are often limitcd and intemal comniunication protocols are complex to achieve real time responses. Thus, the hardware dependent architectural and algorithmic code optimization is applied to improve the perfomlance. The proposed system is tested and optimized on real car environments '. Index Terms About four key words o r phrases in alphabetical order, separated by commas.