计算机与现代化Issue(12)：57-59,70,4.DOI:10.3969/j.issn.1006-2475.2011.12.016
语音识别ASIC中端点检测算法研究与实现
Research and Realization of Endpoint Detection Algorithm in Speech Recognition ASIC
摘要
Abstract
This paper puts forward a simplified two-threshold speech endpoint detection algorithm for speech signal based on short-term energy and zero-crossing rate. Building a simulation platform of Matlab algorithm, and the experimental results show that the two-threshold speech endpoint detection algorithm for speech signal based on short-term energy and zero-crossing rate is better than cepstmm, fractal, and spectrum entropy method of endpoint detection, under the premise of computing complexity and com-putting quantity.This paper completes the various modules of the design, simulation and systems integration with the Verilog language, using fixed-point design approach, the voice signal sampling frequency of 8kHz, the data for each sample 8bits, the internal stability of the chip operates at 20MHz, the coefficient of linear prediction obtained by the circuit compares with simulation results on Matlab platform, the error rate less than 0.2 percent, on conditions of 200 source words, it can achieve an average of more than 90% of the result of recognition.关键词
端点检测:语音识别/专用集成电路Key words
endpoint detection/ speech recognition/ ASIC分类
信息技术与安全科学引用本文复制引用
靳月英..语音识别ASIC中端点检测算法研究与实现[J].计算机与现代化,2011,(12):57-59,70,4.
