Memory and computation reduction for embedded ASR systems
نویسندگان
چکیده
Nowadays, the performance of mobile devices such as personal digital assistants (PDA) or cell phones are rapidly improving. This improvement increased the demand for various functions in mobile devices. Among them, embedded speech recognizers are one of the major research topics. To guarantee an acceptable performance, the efficient usage of the hardware resources is very important. In this paper, we introduce our embedded speech recognizer and several important technologies implemented in it used to reduce hardware resources.
منابع مشابه
Low complexity techniques for embedded ASR systems
This paper deals with the problem of reducing the computational complexity of ASR algorithms for embedded systems. Particularly, three methods for simplifying the computation of state observation likelihoods of continuous density based HMMs are proposed. Feature component masking, variable-rate partial likelihood update and density pruning all result in significant savings in the decoding compl...
متن کاملPerformance Analysis and Optimization of Automatic Speech Recognition
Fast and accurate Automatic Speech Recognition (ASR) is emerging as a key application for mobile devices. Delivering ASR on such devices is challenging due to the compute-intensive nature of the problem and the power constraints of embedded systems. In this paper we provide a performance and energy characterization of Pocketsphinx, a popular toolset for ASR that targets mobile devices. We ident...
متن کاملSide channel parameter characteristics of code injection attacks
Embedded systems are suggestive targets for code injection attacks in the recent years. Software protection mechanisms, and in general computers, are not usually applicable in embedded systems since they have limited resources like memory and process power. In this paper we investigate side channel characteristics of embedded systems and their applicability in code injection attack detection. T...
متن کاملSoftware Virtual Memory Management for MMU-less Embedded Systems
For an embedded system designer, the rise in processing speeds of embedded processors and microcontroller evolution has lead to the possibility of running computation and data intensive applications on small embedded devices that earlier only ran on desktop-class systems. From a memory stand point, there is a similar need for running larger and more data intensive applications on embedded devic...
متن کاملPower Efficient Instruction Caches for Embedded Systems
Instruction caches typically consume 27% of the total power in modern high-end embedded systems. We propose a compiler-managed instruction store architecture (K-store) that places the computation intensive loops in a scratchpad like SRAM memory and allocates the remaining instructions to a regular instruction cache. At runtime, execution is switched dynamically between the instructions in the t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2004