使用自定义 .gram 文件让 Sphinx4 识别所有数字

Question

说明

存在使用Sphinx4 library 的Java 语音识别计算器。

github上的完整代码：here

---

我使用的 gram 文件如下（on github）：

#JSGF V1.0;

/**
 * JSGF Grammar 
 */

grammar grammar;

public <syntax>  = (one | two | three| four| five | six | seven | eight | nine | ten | eleven | twelve | thirteen | fourteen | fifteen | sixteen | seventeen | eighteen | nineteen | twenty) 
                                                          (plus | minus | multiply | division)                          
                   (one | two | three| four| five | six | seven | eight | nine | ten | eleven | twelve | thirteen | fourteen | fifteen | sixteen | seventeen | eighteen | nineteen | twenty);

---

问题：

I want the program to be able to recognize numbers from 0 to 1 million in English Language 。

在当前状态下，您可以看到它可以识别数字(one | two | three| four| five | six | seven | eight | nine | ten | eleven | twelve | thirteen | fourteen | fifteen | sixteen | seventeen | eighteen | nineteen | twenty)，因为我已将它们手动写入gram file。

我的意思是我必须将它们全部手动写入gram file（我可以创建一个程序来生成该文件）但是这似乎是不可能的（可能存在某些模式），该文件将太多千兆字节。

---

最后：

有什么聪明的解决方案吗？谢谢你的努力:)

---

Nikolay之后的新语法解决方法是：

public <number> = (one | two | three | four | five | six | seven | nine | ten
                   | eleven | twelve | thirteen | fourteen | fifteen | sixteen | seventeen | eighteen | nineteen | twenty 
                   | thirty | forty | fifty | sixty  | seventy | eighty | ninety | hundred | thousand | million | billion)+;                   
public <syntax> = <number>{1} (plus | minus | multiply | division){1} <number>{1}; 

Answer 1

最聪明的解决方案是首先识别文本字符串。语法不应该很复杂，应该只列出数字中使用的单词：

 grammar number;

 public <number> = (one | two | three | four | five | six | seven |
 nine | ten | eleven | twelve | thirteen | fourteen | fifteen | 
 sixteen | seventeen | eighteen | nineteen | twenty | thirty | forty | 
 fifty | sixty  | seventy | eighty | ninety | hundred | thousand |
 million | and )*;

识别文本后，将其转换为数字。详情可以查看How to convert words to a number?。