This paper introduces the isolated word speech recognition for system on chip (SoC).
介绍了孤立词语音识别系统，针对片上系统进行了语音识别算法的选择。
We will give experiment results of tone recognition for isolated word and continuous speech.
我们将给出孤立字和连续语音情况下的实验结果。
The system takes isolated word recognition as the core with emphasis on its reliability and generality.
该系统以孤立词语音识别为核心，着重于系统的可靠性和实用性。
The method is available for isolated word and double-syllabic word and is applicable for Chinese continuous speech.
此方法对孤立字和二字词同样有效，并可应用于汉语连续语音。
Tone extraction and recognition of trisyllabic word is more difficult than that of isolated word, because it holds the characteristic of syllable in continuous speech.
三字词音节声调模式具有连续语音中音节声调模式的特征，声调的提取和识别远较孤立字困难。
In isolated word recognition of Chinese considering the trend of information entropy the result is obtained that the number of the state in HMM about 6 is the best selection.
考虑到信息熵的变化趋势，得出语音识别时hmm状态数并非越多越好的结论，指出了汉语单字hmm的状态数取6为宜。
In this paper, a Chinese isolated word recognition system is established based on the source-filter generation model combined with the acoustic characteristics of whispered speech.
本文根据耳语音信号发音模型，结合耳语音的声学特性，建立了一个汉语耳语音孤立字识别系统。
This paper proposes an algorithm based on likelihood difference for isolated-word speech recognition system.
本文提出了一种孤立词语音识别系统中基于后验概率差值的拒识算法。
The word digital has become an integral part of what we produce and deliver as an agency, no longer does digital live in an isolated context.
作为一家媒介代理机构，“数字”这个词对于我们创意概念的出品和传递十分重要，而且它已不再是一个单独孤立的词语。
The two algorithms are implemented using MATLAB, and experiments of isolated-word recognition are done.
然后用MATLAB实现了这两种算法，并进行了大量的孤立词语音识别实验。
By this algorithm, the precise sample data of isolated Chinese word utterance can be obtained, Experiments show that this algorithm is simple and effective.
利用该算法可获得输入信号有声部份的抽样数据，即得到输入汉语词汇声音的准确抽样数据。实验表明，该算法是简易的、行之有效的。
By this algorithm, the precise sample data of isolated Chinese word utterance can be obtained, Experiments show that this algorithm is simple and effective.
利用该算法可获得输入信号有声部份的抽样数据，即得到输入汉语词汇声音的准确抽样数据。实验表明，该算法是简易的、行之有效的。
应用推荐