Systems and methods for generating markup-language based expressions from multi-modal and unimodal inputs
View Patent ↗When using finite-state devices to perform various functions, it is beneficial to use finite state devices representing regular grammars with terminals having markup-language-based semantics. By using markup-language-based symbols in the finite state devices, it is possible to generate valid markup-language expressions by concatenating the symbols representing the result of the performed function. The markup-language expression can be used by other applications and/or devices. Finite-state devices are used to convert strings of words and gestures into valid markup-language, for example, XML, expressions that can be used, for example, to provide an application program interface to underlying system applications.
1. A method comprising:
generating, via a processor, from an first input lattice representing a speech modality of an input, a first markup-language expression;
generating, via the processor, from a second input lattice representing a second modality of the input, a second markup-language expression, wherein the second modality is not speech, the first markup-language expression and the second markup-language expression being unusable in that form by a first application that provides a first function and a second application performing a second function on the input;
generating, via a finite-state transducer, a mapping, wherein the finite-state transducer uses the first input lattice and a finite-state machine having associated markup-language semantics to relate the first markup-language expression to the second markup-language expression;
generating, using the input and a second finite-state machine representing the mapping, a sequence of symbols;
concatenating the sequence of symbols, to yield a concatenated third markup-language expression;
parsing the concatenated third markup-language expression to yield a parsed markup-language expression;
performing the first function to provide a route to a destination via use of the first application and the parsed markup-language expression; and
performing the second function on the input via use of the second application and the parsed markup-language expression, wherein the first application differs from the second application.
2. The method of claim 1 , wherein the second modality is a haptic modality.
3. The method of claim 1 , further comprising concatenating the mapping prior to generating of the third markup-language expression.
4. The method of claim 1 , wherein the finite-state machine uses extensible-markup-language-based symbols.
5. The method of claim 1 , wherein the input further comprises a command received via one of a speech input subsystem, a pen input subsystem, a computer vision input subsystem, a haptic input subsystem, a gaze input subsystem, and a body motion input subsystem.
6. The method of claim 1 , wherein the concatenated third markup-language expression represents sequences of symbols.
7. The method of claim 1 , further comprising performing multimodal integration of the input for use in generating of the mapping.
8. The method of claim 1 , further comprising:
recognizing a gesture string in the input; and
modifying a language model based on the gesture string prior to performing the generating of the mapping.
9. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
generating from an first input lattice representing a speech modality of an input, a first markup-language expression;
generating, via the processor, from a second input lattice representing a second modality of the input, a second markup-language expression, wherein the second modality is not speech, the first markup-language expression and the second markup-language expression being unusable in that form by a first application that provides a first function and a second application performing a second function on the input;
generating, via a finite-state transducer, a mapping, wherein the finite-state transducer uses the first input lattice and a finite-state machine having associated markup-language semantics to relate the first markup-language expression to the second markup-language expression;
generating, using the input and a second finite-state machine representing the mapping, a sequence of symbols;
concatenating the sequence of symbols, to yield a concatenated third markup-language expression;
parsing the concatenated third markup-language expression to yield a parsed markup-language expression;
performing the first function to provide a route to a destination via use of the first application and the parsed markup-language expression; and
performing the second function on the input via use of the second application and the parsed markup-language expression, wherein the first application differs from the second application.
10. The system of claim 9 , wherein the second modality is a haptic modality.
11. The system of claim 9 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising concatenating the mapping prior to generating of the third markup-language expression.
12. The system of claim 9 , wherein the finite-state machine uses extensible-markup-language-based symbols.
13. The system of claim 9 , wherein the input further comprises a command received via one of a speech input subsystem, a pen input subsystem, a computer vision input subsystem, a haptic input subsystem, a gaze input subsystem, and a body motion input subsystem.
14. The system of claim 9 , wherein the concatenated third markup-language expression represents sequences of symbols.
15. The system of claim 9 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising multimodal integration of the input.
16. The system of claim 9 , the computer-readable storage medium having additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
recognizing a gesture string in the input; and
modifying a language model based on the gesture string prior to performing the generating of the mapping.
17. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
generating from an first input lattice representing a speech modality of an input, a first markup-language expression;
generating, via the processor, from a second input lattice representing a second modality of the input, a second markup-language expression, wherein the second modality is not speech, the first markup-language expression and the second markup-language expression being unusable in that form by a first application that provides a first function and a second application performing a second function on the input;
generating, via a finite-state transducer, a mapping, wherein the finite-state transducer uses the first input lattice and a finite-state machine having associated markup-language semantics to relate the first markup-language expression to the second markup-language expression;
generating, using the input and a second finite-state machine representing the mapping, a sequence of symbols;
concatenating the sequence of symbols, to yield a concatenated third markup-language expression;
parsing the concatenated third markup-language expression to yield a parsed markup-language expression;
performing the first function to provide a route to a destination via use of the first application and the parsed markup-language expression; and
performing the second function on the input via use of the second application and the parsed markup-language expression, wherein the first application differs from the second application.
18. The computer-readable storage device of claim 17 , wherein the second modality is a haptic modality.
19. The computer-readable storage device of claim 17 , having additional instructions stored which, when executed by the computing device, cause the computing device to perform operations comprising concatenating the mapping prior to generating of the third markup-language expression.
20. The computer-readable storage device of claim 17 , wherein the finite-state machine uses extensible-markup-language-based symbols.