对三种剪枝方法产生的发音字典的识别结果进行了对比。
The resulting pronunciation candidates are used to expand pronunciation dictionary for non-native speech recognition.
实验结果表明,使用相对最大剪枝策略产生的发音字典可以显著提高系统识别率。
Experimental results on continuous speech recognition show significant improvement can be obtained using resulting pronunciation dictionary.
我们可以从字典中了解单词的拼写、词性、发音、意思和一些句子。
We can get the word spelling, parts of speech, pronunciation, meaning and some sentences in the dictionary.
应用推荐