Claims
- 1. A speech-optimized information apparatus for speech-controlled interactive applications, comprising:
a plurality of grammars for placing constraints on a sequence of words allowed in user utterances made in connection with user application interaction; and means for organizing said grammars to provide high recognition accuracy for said user utterances from a large and continually expanding set of words and phrases without requiring users to provide samples of their voices ahead of time for training.
- 2. The apparatus of claim 1, said plurality of grammars further comprising:
a user application interaction information space organized by information type.
- 3. The apparatus of claim 2, said information space further comprising:
means for allowing user accessible information to be linked or organized into a hierarchy; and means for establishing a user chosen path to navigate through said information.
- 4. The apparatus of claim 1, wherein information in said grammars is used to carry out requests initiated by buttons on a remote control or other such device.
- 5. A method for speech control of interactive applications, comprising the steps of:
providing at least one speech-controlled application that uses a set of commands initiated by either speech or, optionally, by input from a device; providing a set of grammars, composed of utterances, in which speech commands are specified, wherein said grammars comprise:
a set of items, wherein each item comprises a word or phrase that can be spoken; an associated set of attributes that provide more information about said item; an associated set of attributes that provide more information about said grammar as a whole; and optionally, a name of a grammar that must be imported to complete an utterance.
- 6. The method of claim 5, wherein at least one grammar comprises a command grammar for utterances that are used to control said application.
- 7. The method of claim 5, wherein at least one grammar comprises an information-type specific grammar comprising multiple alternatives for a single piece of information.
- 8. The method of claim 7, wherein said information-type specific grammar is linked to another grammar via a unique utterance (keyword) that distinguishes an information type from any other information type.
- 9. The method of claim 8, wherein said information-type specific grammar comprises an attribute that specifies a keyword; and wherein items in said information-type specific grammar comprise an attribute that identifies said item's information type.
- 10. The method of claim 5, further comprising the step of:
providing a chained command attribute indicates that an utterance in an item is a part of a chained command; wherein speech commands are chained together to provide one-step access to information or application functionality.
- 11. A method for speech control of interactive applications, comprising the steps of:
providing a recognizer; providing a command processor; providing a context manager; providing a data source; said context manager communicating with said recognizer to activate appropriate grammars for a current context; said user speaking a command; said recognizer returning said spoken command and all associated attributes to said command processor; said command processor accessing said data source, as necessary, to carry out said command; said command processor updating a current context; and outputting results of said command.
- 12. A method for linking grammars into a hierarchy, comprising the steps of:
defining an utterance that links two grammars in two parts; wherein a first part is a keyword, for information-type specific grammars, or a command for command grammars; and wherein contents of said grammar-to-be-linked are imported to include all alternatives for a second part of said utterance.
- 13. The method of claim 13, wherein said grammars link information-type specific information either explicitly or implicitly.
- 14. The method of claim 13, wherein an application predetermines a navigation path and link in all appropriate grammars.
- 15. The method of claim 13, wherein an application relies on type attributes returned to determine which options to make available to a user next.
- 16. An apparatus for speech control of interactive applications, comprising:
at least one speech-controlled application that uses a set of commands initiated by either speech or, optionally, by input from a device; a set of grammars, composed of utterances, in which speech commands are specified, wherein said grammars comprise:
a set of items, wherein each item comprises a word or phrase that can be spoken; an associated set of attributes that provide more information about said item; an associated set of attributes that provide more information about said grammar as a whole; and optionally, a name of a grammar that must be imported to complete an utterance.
- 17. The apparatus of claim 16, wherein at least one grammar comprises a command grammar for utterances that are used to control said application.
- 18. The apparatus of claim 16, wherein at least one grammar comprises an information-type specific grammar comprising multiple alternatives for a single piece of information.
- 19. The apparatus of claim 18, wherein said information-type specific grammar is linked to another grammar via a unique utterance (keyword) that distinguishes an information type from any other information type.
- 20. The apparatus of claim 19, wherein said information-type specific grammar comprises an attribute that specifies a keyword; and wherein items in said information-type specific grammar comprise an attribute that identifies said item's information type.
- 21. The apparatus of claim 16, further comprising:
a chained command attribute indicates that an utterance in an item is a part of a chained command; wherein speech commands are chained together to provide one-step access to information or application functionality.
- 22. The apparatus of claim 16, further comprising:
means for processing a “more like this” command for using a currently selected item type to decide where to look for information that a user wants.
- 23. An apparatus for speech control of interactive applications, comprising:
a data source; a context manager, said context manager communicating with a recognizer to activate appropriate grammars for a current context; a recognizer, said recognizer returning a spoken command and all associated attributes to a command processor; a command processor, said command processor accessing said data source, as necessary, to carry out said spoken command, said command processor updating a current context and outputting results of said command.
- 24. The apparatus of claim 23, wherein said spoken command effects any of:
a targeted search; an exploratory search; and dynamic application generation.
- 25. An apparatus for linking grammars into a hierarchy, comprising:
at least one speech-controlled application that uses a set of commands initiated by either speech or, optionally, by input from a device; a set of grammars, composed of utterances, in which speech commands are specified, wherein said grammars comprise:
a set of items, wherein each item comprises a word or phrase that can be spoken; an associated set of attributes that provide more information about said item; an associated set of attributes that provide more information about said grammar as a whole; and wherein an utterance links two grammars in two parts:
wherein a first part is a keyword, for information-type specific grammars, or a command for command grammars; and wherein contents of said grammar-to-be-linked are imported to include all alternatives for a second part of said utterance.
- 26. The apparatus of claim 25, wherein said grammars link information-type specific information either explicitly or implicitly.
- 27. The apparatus of claim 25, wherein an application predetermines a navigation path and link in all appropriate grammars.
- 28. The apparatus of claim 25, wherein an application relies on type attributes returned to determine which options to make available to a user next.
- 29. The apparatus of claim 25, further comprising:
means for processing a “more like this” command for using a currently selected item type to decide where to look for information that a user wants.
- 30. An apparatus for dynamically constructing a user interface for a speech-controlled application, comprising:
a plurality of grammars comprising a structure of speech commands for said application; said grammars further comprising means for indicating when commands are chained; means for parsing said grammars to obtain said structure; and means for using said parsed structure to auto-generate at least some of said user interface for said application.
Parent Case Info
[0001] This application claims priority and incorporates by reference the Provisional Application No. 60/422,561, filed Oct. 31, 2002 and the Provisional Application No. 60/483,268, filed Jun. 26, 2003.
Provisional Applications (2)
|
Number |
Date |
Country |
|
60422561 |
Oct 2002 |
US |
|
60483268 |
Jun 2003 |
US |