本文论述了一种小词汇量的特定人孤立字实时识别系统。
A specific speaker, isolated words recognition system for small amount of vocabulary is presented.
把共振峰作为特征参数用于一个小词汇量的汉语语音识别系统中，识别正确率达到了98%。
The formant and corresponding bandwidth parameters result in a correct recognition rate of 98% in a small vocabulary mandarin speech recognition system.
现在，你的问题大概更基础：发音上的错误，小词汇量，现在完成时的和条件句的结构的语法问题。
Right now, your problems are probably more basic: mistakes in pronunciation, small vocabulary, grammar problems with the present perfect tense and conditional structures.
应用推荐