S-Space College of Engineering/Engineering Practice School (공과대학/대학원) Dept. of Electrical and Computer Engineering (전기·정보공학부) Others_전기·정보공학부
부 벡터 군집화를 통한 FPGA기반 음성 인식기의 수행 속도 향상 : Execution Speed Improvement of FPGA-based Speech Recognizer using Sub-vector Clustering
Cited 0 time in Web of Science Cited 0 time in Scopus
- Issue Date
- 대한전자공학회 2009년 하계종합학술대회 2009. 7
- Reducing the memory bandwidth is very critical for real-time implementation of a large vocabulary speech recognizer. In this paper, we implemented sub-vector clustering algorithm in hardware to alleviate the problem of much extreme memory access. The experimental result shows that this implementation accelerates acoustic likelihood computation twice faster, and increases the speed of overall recognition by 22%.
- Files in This Item:
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.