摘要
文中将区别性训练(discriminative training)算法运用于基于MSVQ(multi-section vector quantization)孤立词语音识别系统。实验结果表明这两种技术的结合使用使得识别系统具有识别率高、模板体积小,识别速度快的特点,十分有利于在硬件系统上的实现。
In this paper, we present a method for isolated word speech recognition combining MSVQ and discriminative training techniques. The use of these two techniques toghter enables the system to combine the advantages of high recognition rale, small template size and high recognition speed. This system can well meet the requirements of hardware implementation.
出处
《电子测量技术》
2003年第2期15-16,共2页
Electronic Measurement Technology
