Proposed Efficient Architectures and Design Choices in SoPC System for Speech Recognition
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper presents the design of a System on Programmable Chip (SoPC) based on Field Programmable Gate Array (FPGA) for speech recognition in which Mel-Frequency Cepstral Coefficients (MFCC) for speech feature extraction and Vector Quantization for recognition are used. The implementing process of the speech recognition system undergoes the following steps: feature extraction, training codebook, recognition. In the first step of feature extraction, the input voice data will be transformed into spectral components and extracted to get the main features by using MFCC algorithm. In the recognition step, the obtained spectral features from the first step will be processed and compared with the trained components. The Vector Quantization (VQ) is applied in this step. In our experiment, Altera’s DE2 board with Cyclone II FPGA is used to implement the recognition system which can recognize 64 words. The execution speed of the blocks in the speech recognition system is surveyed by calculating the number of clock cycles while executing each block. The recognition accuracies are also measured in different parameters of the system. These results in execution speed and recognition accuracy could help the designer to choose the best configurations in speech recognition on SoPC.
Abstract
This paper presents the design of a System on Programmable Chip (SoPC) based on Field Programmable Gate Array (FPGA) for speech recognition in which Mel-Frequency Cepstral Coefficients (MFCC) for speech feature extraction and Vector Quantization for recognition are used. The implementing process of the speech recognition system undergoes the following steps: feature extraction, training codebook, recognition. In the first step of feature extraction, the input voice data will be transformed into spectral components and extracted to get the main features by using MFCC algorithm. In the recognition step, the obtained spectral features from the first step will be processed and compared with the trained components. The Vector Quantization (VQ) is applied in this step. In our experiment, Altera’s DE2 board with Cyclone II FPGA is used to implement the recognition system which can recognize 64 words. The execution speed of the blocks in the speech recognition system is surveyed by calculating the number of clock cycles while executing each block. The recognition accuracies are also measured in different parameters of the system. These results in execution speed and recognition accuracy could help the designer to choose the best configurations in speech recognition on SoPC.
참고문헌 (10)
- Lawrance Rabiner, "Fundamentals of Speech Recognition" (1993), Prentice Hall PTR
- "The Hidden Markov Model Toolkit (HTK) Book (for HTK version 3.2.1)"[URL]
- V. Amudha, "Software", Hardware Co-Design of HMM based Isolated Digit Recognition System, 2009, pp.4(2), 154~159
- Haitao Zhou, "Design and Implementation of Speech Recognition System Based on Field Programmable Gate Array", Modern Applied Science, 3(8), pp.106~111 (2009)
- Wei Han, "An Efficient MFCC Extraction Method in Speech Recognition", the 2006 IEEE International Symposium on Circuits and Systems (ISCAS), pp.145~148 (2006)
- Wei Han, "A Speech Recognition IC with an Efficient MFCC Extraction Algorithm and Multi-mixture Models", 박사, pp.2006
- S.-T. Pan, "The implementation of speech recognition systems on FPGA - based embedded systems with SOC architecture", International Journal of Innovative Computing, Information and Control, 7(10) (2011)
- O. Cheng, "Hardware-Software Co-design of Automatic Speech Recognition System for Embedded Real-Time Applications", IEEE Transactions on Industrial Electronics, pp.850~859 (2011)
- Weiqian Liang, "Design of speech recognition co-processor with fast Gaussian likelihood computation", the 3rd International Conference on Computer Research and Development (ICCRD), pp.392~395 (2011)
- Ge Zhang, "A real-time speech recognition system based on the Implementation of FPGA", Cross Strait Quad-Regional Radio Science and Wireless Technology Conference (CSQRWC), pp.1375~1378 (2011)