LIÊN KẾT WEBSITE
FPGA architecture of HMM-based decoder module in speech recognizer
2012 International Conference on Control, Automation and Information Sciences, ICCAIS 2012 Số , năm 2012 (Tập , trang 354-358)
DOI: 10.1109/ICCAIS.2012.6466617
Tài liệu thuộc danh mục: Scopus
Conference Paper
English
Từ khóa: Decoder module; Design and implementations; FPGA architectures; HMM-based; Number of state; Recognition accuracy; Reconfigurable; Speech recognition systems; Speech recognizer; Hidden Markov models; Information science; Reconfigurable architectures; Viterbi algorithm; Speech recognition
Tóm tắt tiếng anh
This paper presents the reconfigurable architecture and implementation of HMM-based decoder module in speech recognizer on FPGA. The architecture is done with different parameters of speech recognition system that could be easily reconfigurable. The design and implementation on FPGA have been verified with utterances of 800 test speeches. The implementation results, the recognition accuracy results of up to 98% are also presented. 2012 IEEE.