Optimization of ETSI DSR frontend software on a high-efficient audio DSP

Server-terminal based distributed speech recognition (DSR) applications are widely adopted on mobile devices. In this paper, we have implemented a power-efficient DSR solution of high performance for real-time speech processing. The DSR frontend algorithms are elaborately optimized in assembly codes utilizing accelerating technics provided by a previously released audio DSP, such as binary scaling operations in a deep instruction pipeline, automatic memory addressing method, and parallel processing of packaged data. The performance of DSR frontend software running on the DSP is greatly improved, and our work is of best efficiency compared with former solutions. The realtime frequency of processing 16 kHz input streams is 124.3 MHz and is only about 30% of what is required on a TI C64x DSP. Based on simulation experiment under SMIC 130 nm process, the power consumed for DSR frontend processing is 23 mW. Besides, the presented implementation of the algorithms is also integrated in a server-terminal demo system, and is proved to be worked well in real speech recognition applications.

I. Introduction

Through decades of research and development, speech recognition technology has reached higher and higher accuracy. With the development of mobile computing architecture and the popularity of smart phones, people are able to enjoy the convenience anywhere and anytime brought by speech recognition applications like Google Voice Search and Siri. Constrained to computing capability and battery lifetime of mobile phones, both of the two applications apply distributed terminal-server solutions, which means users' terminals just have to do some preprocessing work, and most computational tasks such as acoustic modeling and feature matching and text are performed on servers.