Oral modification of an ASR lexicon of an ASR engine

1. A method for providing oral modification of an automatic speech recognition (‘ASR’) lexicon of an ASR engine, the method comprising:

receiving, in the ASR engine from a user through a multimodal application, speech for recognition, wherein the ASR engine comprises an ASR lexicon of words that the ASR engine recognizes, and the ASR lexicon does not contain at least one word of the speech for recognition;

indicating by the ASR engine through the multimodal application to the user that the ASR lexicon does not contain the word by returning a message that explicitly indicates that the ASR engine does not recognize the word;

receiving by the ASR engine from the user through the multimodal application an oral instruction to add the word to the ASR lexicon, the oral instruction accompanied by an oral spelling of the word from the user; and

executing the instruction by the ASR engine.

2. The method of claim 1 wherein receiving an instruction to add the at least one word to the ASR lexicon further comprises receiving in the ASR engine from the multimodal application the spelled word in text format.

3. The method of claim 1 wherein executing the instruction further comprises:

adding the spelled word to an active grammar; and

compiling the active grammar into the ASR lexicon after adding the spelled word to the active grammar.

4. The method of claim 1 further comprising determining by the ASR engine that the ASR lexicon does not contain the at least one word.

5. A computer comprising a computer processor and a computer memory operatively coupled to the computer processor, wherein the computer memory stores computer program instructions for providing oral modification of an automatic speech recognition (‘ASR’) lexicon of an ASR engine, and wherein the computer processor executes the computer program instructions to:

receive, from a user through a multimodal application, speech for recognition, wherein the ASR engine comprises an ASR lexicon of words that the ASR engine recognizes, and the ASR lexicon does not contain at least one word of the speech for recognition;

indicate through the multimodal application to the user that the ASR lexicon does not contain the word by returning a message that explicitly indicates that the ASR engine does not recognize the word;

receive from the user through the multimodal application an oral instruction to add the word to the ASR lexicon, the oral instruction accompanied by an oral spelling of the word from the user; and

execute the instruction.

6. The computer of claim 5 wherein the computer processor executes the computer program instructions to determine that the ASR lexicon does not contain the at least one word.

7. The computer of claim 5 wherein the computer processor receives the instruction to add the at least one word to the ASR lexicon by receiving in the ASR engine from the multimodal application the spelled word in text format.

8. The computer of claim 5 wherein the computer processor executes the instruction by:

adding the spelled word to an active grammar; and

compiling the active grammar into the ASR lexicon after adding the spelled word to the active grammar.

9. A tangible computer program product for providing oral modification of an automatic speech recognition (‘ASR’) lexicon of an ASR engine, the computer program product encoded with computer program instructions that, when executed by a computer, perform a method comprising:

receiving, in the ASR engine from a user through a multimodal application, speech for recognition, wherein the ASR engine comprises an ASR lexicon of words that the ASR engine recognizes, and the ASR lexicon does not contain at least one word of the speech for recognition;

indicating by the ASR engine through the multimodal application to the user that the ASR lexicon does not contain the word by returning a message that explicitly indicates that the ASR engine does not recognize the word;

receiving by the ASR engine from the user through the multimodal application an oral instruction to add the word to the ASR lexicon, the oral instruction accompanied by an oral spelling of the word from the user; and

executing the instruction by the ASR engine.

10. The computer program product of claim 9 , wherein the method further comprises determining by the ASR engine that the ASR lexicon does not contain the at least one word.

11. The computer program product of claim 9 wherein receiving an instruction to add the at least one word to the ASR lexicon further comprises receiving in the ASR engine from the multimodal application the spelled word in text format.

12. The computer program product of claim 9 wherein executing the instruction further comprises:

adding the spelled word to an active grammar; and

compiling the active grammar into the ASR lexicon after adding the spelled word to the active grammar.