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

This paper presents an efficient speech interactive agent rendering smooth car navigation and Telematics services, by employing embedded automatic speech recognition (eASR), distributed speech recognition (DSR) and embedded text-to-speech (eTTS) modules, all while enabling safe driving. A speech interactive agent is essentially a conversational tool providing command and control functions to drivers such as enabling navigation task, audio/video manipulation, and E-commerce services through natural voice/response interactions between user and interface. To cope with the multiple 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 negotiation rules using priority control based on inter-process communication, speech interactive helper function, multi-thread process and exception handling. In addition, involved hardware resources are often limited and internal communication protocols are complex to achieve real time responses. Thus, the hardware dependent architectural and algorithmic code optimization is applied to improve the performance. The proposed system is tested and optimized on real car environments.