DocumentCode :
1832603
Title :
The speech recognition chip implementation on FPGA
Author :
Chang, Cheng-Yuan ; Chen, Ching-Fa ; Pan, Shing-Tai ; Li, Xu-Yu
Author_Institution :
Dept. of Electr. Eng., Chung Yuan Christian Univ., Jhongli, Taiwan
Volume :
2
fYear :
2010
fDate :
1-3 Aug. 2010
Abstract :
This paper includes the exploration of using HMM algorithm to construct speech recognition platform which be speeded up on embedded system of FPGA by Integer FFT. On embedded system the computing speed is not as fast as personal computer. This will causes that speech recognition takes much time and power; and further, it didn´t satisfy the real time requirement. In this paper, we use Integer FFT to replace Float FFT. It will be shown that the recognition rate is only lose a little but reduce much computing time.
Keywords :
embedded systems; fast Fourier transforms; field programmable gate arrays; hidden Markov models; speech recognition; FPGA; HMM algorithm; Integer FFT; chip implementation; embedded system; speech recognition; Computational modeling; Hidden Markov models; Speech; Speech processing; Speech recognition; FPGA; Hidden Markov Model; Integer Fast Fourier Transform; Speech Recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Mechanical and Electronics Engineering (ICMEE), 2010 2nd International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4244-7479-0
Electronic_ISBN :
978-1-4244-7481-3
Type :
conf
DOI :
10.1109/ICMEE.2010.5558498
Filename :
5558498
Link To Document :
بازگشت