Specifying arbitrary words in rule-based grammars

• US 7,302,381 B2
• Filed: 12/30/2000
• Issued: 11/27/2007
• Est. Priority Date: 12/30/2000
• Status: Expired due to Fees

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Pokhariyal, Shuvranshu, Aundhe, Shirish, Hernandez, Thomas, Gough, Corey, Davidson, Jason
• Primary Examiner(s): Hudspeth; David
• Assistant Examiner(s): Jackson; Jakieda R.
• Application Number:
  US09/752,994
• Publication Number:
  US 20020123876A1
• Time in Patent Office: 2,523 Days
• Field of Search: 704/9, 704/225, 704/1, 704/209, 704/231, 704/270, 704/258, 704/4, 704/10, 707/104.1, 707/5, 715/536
• US Class Current: 704/1
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks

Abstract

A method and apparatus are described for specifying arbitrary words in a rule-based grammar, such as a context-free grammar. A wildcard identifier is used in a context-free grammar file in place of a predefined category of words. Artificial phoneme combinations that represent generic words in a speech engine'"'"'s vocabulary database, and that represent pronunciations of the predefined category of words are defined by rules. A speech engine uses the artificial phoneme combinations to determine acceptable words to listen to, and generates a results object comprising generic words corresponding to the artificial phoneme combinations, as well as non-generic words that do not exist in a given CFG, where the generic and non-generic words exist in the speech engine'"'"'s vocabulary database. The word having the highest confidence level that is not a generic word is selected as the word most likely to have been spoken by the user.

Claims

1. A method comprising:

creating a rule-based grammar having a wildcard identifier in place of a predefined category of words;

defining rules to produce artificial combinations of unique sounds in a language, where each artificial combination represents a pronunciation of the words in the predefined category, and represents a generic word that is defined in a speech engine'"'"'s vocabulary database;

generating a set of artificial combinations of unique sounds by substituting the wildcard identifier with the rules; and

in response to human speech specifying a wildcard word, determining a set of potential words spoken by the user by finding the generic words and non-generic words that phonetically match the wildcard word, wherein the non-generic words are not part of the rule-based grammar, assigning each of the generic and non-generic words a confidence level based on a set of rules followed by the speech engine, wherein the generic and non-generic words that are part of a particular application are assigned a higher confidence level than the generic and non-generic words that are not part of the particular application, removing the generic words from the set of potential words spoken by the user, and selecting a remaining non-generic word from the set of potential words spoken by the user having a highest confidence level.

2. The method of claim 1, wherein the rule-based grammar comprises a context-free grammar (CFG).

3. The method of claim 1, wherein a unique sound in a language comprises a phoneme.

4. The method of claim 1, wherein said generating a set of artificial combinations of unique sounds by substituting the wildcard identifier with the rules comprises converting the wildcard rule-based grammar into a standard rule-based grammar.

5. A method comprising:

specifying a wildcard context-free grammar (CFG) which includes a wildcard identifier in place of a predefined category of words, each of which are defined in the speech engine'"'"'s vocabulary database;

specifying a set of rules that define artificial combinations of unique sounds in a language, where each artificial combination represents a pronunciation of the words in the predefined category, and corresponds to a generic word that is defined in a speech engine'"'"'s vocabulary database;

converting the wildcard CFG file into a recognized CFG grammar file by generating a set of artificial combinations of unique sounds based on the rules; and

in response to human speech having one or more spoken units, generating a results object having a number of generic words corresponding to artificial combinations appropriate to a given spoken unit, and having a number of non-generic words in the speech engine'"'"'s vocabulary database appropriate to a given spoken unit, wherein the non-generic words are not part of the CFG, each generic word and non-generic word having an associated confidence level based on a set of rules followed by the speech engine, wherein the generic and non-generic words that are part of a particular application are associated with a higher confidence level than the generic and non-generic words that are not part of the particular application, removing the generic words from the results object, and selecting a remaining non-generic word from the results object having a highest confidence level.

6. The method of claim 5, additionally comprising querying the results object for a word having the highest confidence level in the speech engine'"'"'s vocabulary database.

7. The method of claim 5, wherein a unique sound in a language comprises a phoneme.

8. A tangible machine-readable medium having stored thereon data representing sequences of instructions, the sequences of instructions which, when executed by a processor, cause the processor to perform the following:

create a rule-based grammar having a wildcard identifier in place of a predefined category of words;

define rules to produce artificial combinations of unique sounds in a language, where each artificial combination represents a pronunciation of the words in the predefined category, and represents a generic word that is defined in a speech engine'"'"'s vocabulary database;

generate a set of artificial combinations of unique sounds by substituting the wildcard identifier with the rules; and

in response to human speech specifying a wildcard word, determine a set of potential words spoken by the user by finding the generic words and non-generic words that phonetically match the wildcard word, wherein the non-generic words are not part of the rule-based grammar, assigning each of the generic and non-generic words a confidence level based on a set of rules followed by the speech engine, wherein the generic and non-generic words that are part of a particular application are assigned a higher confidence level than the generic and non-generic words that are not part of the particular application, removing the generic words from the set of potential words spoken by the user, and selecting a remaining non-generic word from the set of potential words spoken by the user having a highest confidence level.

9. The tangible machine-readable medium of claim 8, wherein the rule-based grammar comprises a context-free grammar (CFG).

10. The tangible machine-readable medium of claim 8, wherein a unique sound in a language comprises a phoneme.

11. An apparatus comprising:

at least one processor; and

a machine-readable medium having instructions encoded thereon, which when executed by the processor, are capable of directing the processor to;

create a rule-based grammar having a wildcard identifier in place of a predefined category of words;

define rules to produce artificial combinations of unique sounds in a language, where each artificial combination represents a pronunciation of the words in the predefined category, and represents a generic word that is defined in a speech engine'"'"'s vocabulary database;

generate a set of artificial combinations of unique sounds by substituting the wildcard identifier with the rules; and

in response to human speech specifying a wildcard word, determine a set of potential words spoken by the user by finding the generic words and non-generic words that phonetically match the wildcard word, wherein the non-generic words are not part of the rule-based grammar, assigning each of the generic and non-generic words a confidence level based on a set of rules followed by the speech engine, wherein the generic and non-generic words that are part of a particular application are assigned a higher confidence level than the generic and non-generic words that are not part of the particular application, removing the generic words from the set of potential words spoken by the user, and selecting a remaining non-generic word from the set of potential words spoken by the user having a highest confidence level.

12. The apparatus of claim 11, wherein the rule-based grammar comprises a context-free grammar (CFG).

13. The apparatus of claim 11, wherein a unique sound in a language comprises a phoneme.

14. An apparatus comprising:

means for creating a rule-based grammar having a wildcard identifier in place of a predefined category of words;

means for defining rules to produce artificial combinations of unique sounds in a language, where each artificial combination represents a pronunciation of the words in the predefined category, and represents a generic word that is defined in a speech engine'"'"'s vocabulary database;

means far generating a set of artificial combinations of unique sounds by substituting the wildcard identifier with the rules; and

in response to human speech specifying a wildcard word, means for determining a set of potential words spoken by the user by finding the generic words and non-generic words that phonetically match the wildcard word, wherein the non-generic words are not part of the rule-based grammar, assigning each of the generic and non-generic words a confidence level based on a set of rules followed by the speech engine, wherein the generic and non-generic words that are part of a particular application are assigned a higher confidence level than the generic and non-generic words that are not part of the particular application, removing the generic words from the set of potential words spoken by the user, and selecting a remaining non-generic word from the set of potential words spoken by the user having a highest confidence level.

15. The apparatus of claim 14, wherein the rule-based grammar comprises a context-free grammar (CFG).

16. The apparatus of claim 14, wherein a unique sound in a language comprises a phoneme.

17. A system comprising:

a conversion module to accept a wildcard rule-based grammar file as input, wherein the rule-based grammar has a wildcard identifier in place of a predefined category of words, wherein the rule-based grammar defines rules to produce artificial combinations of unique sounds in a language, and to convert the wildcard rule-based grammar file to a set of artificial combinations of unique sounds in a language by substituting the wildcard identifier with the rules;

a speech engine to accept human speech having a wildcard word as input, and to determine a set of potential words matching the wildcard word, the set of potential words comprising a number of generic words and non-generic words corresponding to the artificial combinations of unique sounds in a language, wherein the non-generic words are not part of the rule-based grammar; and

a speech adapter to interact with the speech engine by querying the speech engine for potential words matching the wildcard word, wherein each of the generic and non-generic words are assigned a confidence level based on a set of rules followed by the speech engine, wherein the generic and non-generic words that are part of a particular application are assigned a higher confidence level than the generic and non-generic words that are not part of the particular application, wherein the generic words are removed from the set of potential words, wherein a remaining non-generic word from the set of potential words having a highest confidence level is selected, and returning the selected word which is most likely to match the wildcard word spoken by the user.

18. The system of claim 17, wherein the unique sounds in a language comprise phonemes.

19. The system of claim 17, wherein the rule-based grammar is a context-free grammar (CFG).

20. The system of claim 17, wherein the speech engine comprises the conversion module.