Intelligent speech recognition of incomplete phrases

• US 20080059186A1
• Filed: 08/31/2006
• Published: 03/06/2008
• Est. Priority Date: 08/31/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Wu, Qiang, Mowatt, David, Plumpe, Michael D., Schmid, Philipp Heinz, Brown, Robert Ian, Loynd, Ricky, Dewar, Robert Edward, Morton, Rachel Imogen
• Granted Patent: US 7,949,536 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Intelligent speech recognition is used to provide users with the ability to utter more user friendly commands. Satisfaction is increased when a user can vocalize a subset of a formal command name and still have the intended command identified and processed. Moreover, greater accuracy in identifying a command application from a user'"'"'s utterance can be achieved by ignoring command choices associated with unlikely user utterances. An intelligent speech recognition system can identify differing acceptable verbal command phrase forms, e.g., but not limited to, complete commands, command subsequences and command subsets, for different commands supported by the system. Subset blocking words are identified for assistance in reducing the ambiguity in matching user verbal command phrases with valid commands supported by the intelligent speech recognition system.

Claims

1. A method for identifying verbal phrases, the method comprising:

defining a context free grammar for an application command of an application wherein the context free grammar identifies at least one valid subset for the application command;

receiving a verbal phrase from a computing device user;

generating a recognition for the verbal phrase using the context free grammar;

associating the recognition with the application command; and

providing the application command to the application for processing.

2. The method for identifying verbal phrases of claim 1, further comprising:

generating a subset blocking word list that comprises at least one subset blocking word; and

defining the context free grammar for the application command using an option that designates subsets as the acceptable verbal phrase form for the application command.

3. The method for identifying verbal phrases of claim 2, wherein the subset blocking word list is used to generate the recognition.

4. The method for identifying verbal phrases of claim 1, wherein each of the at least one valid subset identified by the context free grammar for the application command has at least one non subset blocking word.

5. The method for identifying verbal phrases of claim 1, wherein any of the at least one valid subset for the application command can be a subsequence for the application command and wherein one of the at least one valid subset for the application command can be the application command.

6. The method for identifying verbal phrases of claim 1, wherein the application command of claim 1 is a first application command, further comprising:

defining a context free grammar for a second application command of the application wherein the context free grammar for the second application command identifies at least one valid subset for the second application command;

generating a second recognition for the verbal phrase using the context free grammar for the second application command;

associating the second recognition with the second application command;

assigning a score to the first recognition;

assigning a score to the second recognition wherein the score assigned the first recognition is greater than the score assigned to the second recognition; and

providing the first application command to the application for processing as it is the application command associated with the first recognition with an assigned score greater than the score assigned the second recognition.

7. The method for identifying verbal phrases of claim 6, wherein one context free grammar identifies the at least one valid subset for the first application command and the at least one valid subset for the second application command.

8. The method for identifying verbal phrases of claim 1, wherein the application command is a first application command, further comprising defining a context free grammar for a second application command wherein the second application command is parsed into at least two application command phrases wherein the at least two application command phrases combined represent the entire second application command, and wherein at least one of the at least two application command phrases is defined by the context free grammar such that a subset of the at least one of the at least two application command phrases is a valid verbal phrase for the at least one of the at least two application command phrases.

9. A method for identifying incomplete verbal commands, the method comprising:

generating a subset blocking word list that comprises at least one subset blocking word;

establishing a context free grammar for an application command of an application wherein the context free grammar identifies at least one valid subset for the application command;

receiving an incomplete verbal command from a computing device user;

using the incomplete verbal command, the subset blocking word list and the context free grammar to generate a recognition for the incomplete verbal command;

identifying the recognition with the application command; and

notifying the application to process the application command.

10. The method for identifying incomplete verbal commands of claim 9, wherein a subset blocking word of the subset blocking word list is a content-free word.

11. The method for identifying incomplete verbal commands of claim 9, wherein generating a subset blocking word list comprises:

including a word in the subset blocking word list if the frequency of the word in the language of the application command is greater than a predetermined threshold; and

including a word in the subset blocking word list if the phonemic length of the word is less than a predetermined value.

12. The method for identifying incomplete verbal commands of claim 11, wherein generating a subset blocking word list further comprises including a word or phrase in the subset blocking word list for a punctuation mark.

13. The method for identifying incomplete verbal commands of claim 9, wherein the application command is a first application command, further comprising:

establishing a context free grammar for a second application command of the application wherein the context free grammar for the second application command identifies at least one valid subset for the second application command;

using the incomplete verbal command, the subset blocking word list and the context free grammar for the second application command to generate a second recognition for the incomplete verbal command; and

requesting the computing device user identify the first application command or the second application command as the command intended by the incomplete verbal command.

14. The method for identifying incomplete verbal commands of claim 9, wherein the application command is a first application command, further comprising defining a context free grammar for a second application command wherein the second application command is parsed into at least two application command phrases which are each a subsequence of the second application command, and wherein each of the at least two application command phrases is defined by a context free grammar that identifies a valid subset for the application command phrase.

15. The method for identifying incomplete verbal commands of claim 14, wherein the recognition identified with the first application command is a first recognition, and wherein a second recognition is identified with the second application command when phrases of the incomplete verbal command each match a valid subset identified for each of the application command phrases of the second application command.

16. A method for identifying verbal commands, the method comprising:

defining a context free grammar for a first application command of an application wherein the context free grammar for the first application command identifies at least one valid subset for the first application command;

defining a context free grammar for a second application command of an application wherein the context free grammar for the second application command identifies at least one valid subset for the second application command;

receiving a verbal command from a computing device user;

generating a recognition for the verbal command using the verbal command and the context free grammar for the first application command; and

identifying the recognition with the first application command.

17. The method for identifying verbal commands of claim 16, further comprising:

generating a second recognition for the verbal command using the verbal command and the context free grammar for the second application command;

identifying the second recognition with the second application command;

determining that the verbal command;

from the computing device user was intended to identify the first application command; and

notifying the application to process the first application command.

18. The method for identifying verbal commands of claim 17, wherein determining that the verbal command from the computing device user was intended to identify the first application command comprises requesting the computing device user to choose between the first application command and the second application command.

19. The method for identifying verbal commands of claim 16, wherein the context free grammar for the first application command is a first context free grammar and the context free grammar for the second application command is a second context free grammar.

20. The method for identifying verbal commands of claim 16, further comprising

generating a subset blocking word list;

and

using the subset blocking word list when generating a recognition for the verbal command.