HARDWARE IMPLEMENTATION OF DISTRIBUTED SPEECH RECOG NITION SYSTEM FRONT END
msra(2009)
摘要
Modern speech recognition applications are heading to- wards embedded systems and hand-held devices. Distributed Speech Recognition (DSR) system architecture emerged to address this kind of applications. Most of the exis ting im- plementations of this system are presented in softw are fash- ion, with little consideration to the end product p latform in which the system will be deployed. In this paper, a n opti- mized hardware implementation of the front end part of the DSR specified in the basic ETSI Aurora standard ETS I ES 201 108 is presented in FPGA platform prototype, wi th con- sideration of migration to structured ASIC in case of mass- production. Main design issues and tips are highlig hted. Results are presented in terms of hardware resource s utiliza- tion, comparison of some basic system components to third party reference designs and compliance to the Auror a stan- dard.
更多查看译文
关键词
fpga platform prototype,third party reference designs,distributed speech recognition system front end,basic system components,etsi aurora standard etsi es 201 108,hand-held devices,speech recognition,handheld devices,structured asic,hardware implementation,hardware resource utilization,asic,mass production,application specific integrated circuits,software fashion,end product platform,embedded systems,field programmable gate arrays,basic etsi aurora standard etsi es 201 108,dsr system architecture,hardware,mel frequency cepstral coefficient,decoding
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络