Method and system of building a grammar rule with baseforms generated dynamically from user utterances

• US 20060047510A1
• Filed: 08/24/2004
• Published: 03/02/2006
• Est. Priority Date: 08/24/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Muschett, Brien H., Cross, Charles W. Jr., Ativanichayaphong, Soonthorn
• Granted Patent: US 7,487,085 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering

Abstract

A method (200) of building a grammar with baseforms generated dynamically from user utterances can include the steps of recording (205) a user utterance, generating (210) a baseform using the user utterance, creating or adding to (215) a grammar rule using the baseform, and binding (230) the grammar rule in a grammar document of a voice extensible markup language program. Generating a baseform can optionally include introducing a new element to VoiceXML with attributes that enable generating the baseform from a referenced recording such as the user utterance. In one embodiment, the method can be used to create (235) a phonebook and a grammar to access the phonebook by repeatedly visiting a form containing the grammar rule with attributes that enable generating the baseform from the referenced recording.

Claims

1. A method of building a grammar with baseforms generated dynamically from user utterances, comprising the steps of:

recording a user utterance;

generating a baseform using the user utterance;

performing at least one of creating a grammar rule using the baseform and adding to a grammar rule using the baseform; and

binding the grammar rule of the performing step in a grammar document of a voice extensible markup language program.

2. The method of claim 1, wherein the step of generating a baseform comprises introducing a new element to VoiceXML with attributes that enable generating the baseform from a referenced recording.

3. The method of claim 2, wherein the referenced recording comprises the user utterance.

4. The method of claim 2, wherein the grammar rule is constructed using values of the attributes.

5. The method of claim 2, wherein the method further comprises the step of creating a grammar token when the new element is visited by a form interpretation algorithm.

6. The method of claim 5, wherein the method further comprises the step of controlling a composition of the grammar rule as the grammar token is added to the grammar rule.

7. The method of claim 2, wherein the method further comprises the step of creating a phonebook and a grammar to access the phonebook by repeatedly visiting a form containing the grammar rule with attributes that enable generating the baseform from the referenced recording.

8. A system having an automatic speech recognition application, comprising:

a memory for storing a list of user utterances and associated grammars;

a processor coupled to the memory, wherein the processor is programmed to;

record a user utterance;

generate a baseform using the user utterance;

perform at least one of creating a grammar rule using the baseform and adding to a grammar rule using the baseform; and

bind the grammar rule associated with the perform action above in a grammar document of a voice extensible markup language program.

9. The system of claim 8, wherein the processor is programmed to generate a baseform by introducing a new element to VoiceXML with attributes that enable generating the baseform from a referenced recording.

10. The system of claim 9, wherein the referenced recording comprises the user utterance.

11. The system of claim 9, wherein the grammar rule is constructed using values of the attributes.

12. The system of claim 9, wherein the processor is further programmed to create a grammar token when the new element is visited by a form interpretation algorithm.

13. The system of claim 12, wherein the processor is further programmed to control a composition of the grammar rule as the grammar token is added to the grammar rule.

14. The system of claim 9, wherein the processor is further programmed to create a phonebook and a grammar to access the phonebook by repeatedly visiting a form containing the grammar rule with attributes that enable generating the baseform from the referenced recording.

15. A machine-readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

recording a user utterance;

generating a baseform using the user utterance;

performing at least one of creating a grammar rule using the baseform and adding to a grammar rule using the baseform; and

binding the grammar rule in a grammar document of a voice extensible markup language program.

16. The machine-readable storage of claim 15, wherein the machine-readable storage further comprises code sections for causing the machine to generate a baseform by introducing a new element to VoiceXML with attributes that enable generating the baseform from a referenced recording.

17. The machine-readable storage of claim 16, wherein the referenced recording comprises the user utterance.

18. The machine-readable storage of claim 16, wherein the grammar rule is constructed using values of the attributes.

19. The machine-readable storage of claim 16, wherein the machine-readable storage further comprises code sections for causing the machine to create a grammar token when the new element is visited by a form interpretation algorithm.

20. The machine-readable storage of claim 19, wherein the machine-readable storage further comprises code sections for causing the machine to control a composition of the grammar rule as the grammar token is added to the grammar rule.

21. The machine-readable storage of claim 16, wherein the machine-readable storage further comprises code sections for causing the machine to create a phonebook and a grammar to access the phonebook by repeatedly visiting a form containing the grammar rule with attributes that enable generating the baseform from the referenced recording.