Title :
Design of speech recognition co-processor with fast gaussian likelihood computation
Author :
Li, Li ; Liang, Weiqian ; Geng, Hui
Author_Institution :
Dept. of Electron. Eng., Tsinghua Univ., Beijing, China
Abstract :
This paper presents the design of high performance co-processor used to calculate the posterior probabilities for the embedded speech recognition of CHMM (Continuous Hidden Markov Model) with the MPIE (Maximum Probability Increase Estimation) algorithm to finish the most computation intensive operations in the speech recognition flow. The design of the co-processor is verified on Xilinx FPGA platform with ARM as MCU.
Keywords :
Gaussian processes; coprocessors; digital signal processing chips; field programmable gate arrays; hidden Markov models; probability; speech recognition; ARM; MCU; Xilinx FPGA platform; continuous hidden Markov model; embedded speech recognition; fast Gaussian likelihood computation; maximum probability increase estimation algorithm; posterior probability; speech recognition coprocessor design; Hardware; Hidden Markov models; Indexes; Random access memory; Software; Speech; Speech recognition; ARM; ASR; HMM; MPIE; co-processor; speech recognition;
Conference_Titel :
Computer Research and Development (ICCRD), 2011 3rd International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-61284-839-6
DOI :
10.1109/ICCRD.2011.5764221
