System and method for providing locale-specific interpretation of text data

• US 20040030554A1
• Filed: 01/09/2002
• Published: 02/12/2004
• Est. Priority Date: 01/09/2002
• Status: Abandoned Application

• Current Assignee: Openwave Systems Incorporated (JP Morgan Chase & Co)
• Original Assignee: Openwave Systems Incorporated (JP Morgan Chase & Co)
• Inventors: Cong, Lin, Boxberger-Oberoi, Samya
• Application Number:
  US10/043,878
• Publication Number:
  US 20040030554A1
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 2203/2061 Language aspects
• CPC Class Codes: H04M 2203/4509 Unified messaging with single point of access to voicemail and other mail or messaging systems unified messaging in packet switching networks H04L51/56
• CPC Class Codes: H04M 2242/14 with services dependent on location where the service is an information service H04M2242/15; services independent of location H04M3/42229
• CPC Class Codes: H04M 3/53 Centralised arrangements for recording incoming messages , i.e. mailbox systems
• CPC Class Codes: H04M 3/53383 Message registering commands or announcements; Greetings

Abstract

A system and method for generating native-sounding speech in a system prompt or in a text-to-speech processor or application is disclosed. A number of locales are defined representing particular languages, regions and dialects, and a set of locale-specific rules are defined for each locale. The locale-specific rules define how certain types of words, symbols, characters, punctuation and other elements should be interpreted. The locale-specific rules are used by a messaging system to generate native-sounding prompts that are played for callers. The locale-specific rules may also be used by a text-to-speech process to generate native-sounding speech for the user. The locale-specific rules may be implemented in a software class, program or application. The locale-specific rules incorporate a hierarchical structure in which rules that are common to a number of languages are grouped at one level and more specific rules are organized at lower levels in the hierarchy.

Claims

1. A system for providing text interpretation rules for a text-to-speech engine, comprising:

a text-to-speech engine that receives text-based information and converts the text-based information to spoken words;

a set of locale-specific rules that define how certain text-based information should be interpreted in the text-to-speech engine, wherein said set of locale-specific rules include text interpretation rules for a plurality of languages, dialects or locations.

2. The system of claim 1 further comprising:

a text message storage device for storing a plurality of text messages, wherein said text messages may be transmitted to the text-to-speech engine for conversion to a corresponding audio message.

3. The system of claim 1 further comprising:

a processor for identifying a desired locale to be used for conversion of a text-based information.

4. The system of claim 3 wherein said desired locale corresponds to a locale identified by a user who will receive converted text-based information.

5. The system of claim 3 wherein said desired locale corresponds to a locale that is associated with the text-based information that is to be converted.

6. The system of claim 1 wherein said set of locale-specific rules are organized in a hierarchical manner in which text interpretation rules that are common to two or more locales are grouped at one level and wherein text interpretation rules that are specific to a particular locale are grouped at a lower level on the hierarchy.

7. A method for providing native-sounding messages when converting text to speech, comprising:

identifying a selected locale to be used when converting said text to speech;

identifying one or more elements in said text that should be interpreted using locale-specific rules; and

accessing a set of locale-specific rules for instructions regarding how to convert said one or more elements to speech, wherein said locale-specific rules are associated with said selected locale.

8. The method of claim 7 wherein said one or more elements are selected from the group consisting of:

numbers,

characters,

symbols,

abbreviations, and

punctuation marks.

9. The method of claim 7 further comprising:

identifying one or more numbers in said text; and

determining a number type of said one or more numbers.

10. The method of claim 9 wherein said number type is selected from the group consisting of:

a time;

a date;

a key number;

a telephone number;

a duration number;

an address number; and

a counting number.

11. The method of claim 7 wherein said one or elements are case-sensitive for the selected locale;

and the method further comprising;

determining a proper case to be used for said one or more elements when the one or more elements are converted to speech.

12. The method of claim 7 wherein said one or more numbers are gender-sensitive for the selected locale;

and the method further comprising;

means for determining a proper gender to be used for said one or more elements when the one or more elements are converted to speech.

13. A method for converting numbers in a text file to native-sounding speech, comprising:

identifying digits in the text file that is being converted to speech;

classifying the digits as a time, date or number;

identifying a selected locale that is associated with the text file; and

accessing a set of locale-specific rules for the selected locale to determine how to convert the digits to speech.

14. The method of claim 13 further comprising:

classifying a time as a 12-hour time format or a 24-hour time format.

15. The method of claim 13 further comprising:

identifying a date format for the digits.

16. The method of claim 13 further comprising:

identifying a number format for the digits.

17. The method of claim 13 wherein a use of the digits in the text is case sensitive, and the method further comprising:

identifying a case for the digits before the digits are converted to speech.

18. The method of claim 13 wherein a use of the digits in the text is gender sensitive, and the method further comprising:

identifying a gender for the digits before the digits are converted to speech.

19. A method for providing native-sounding prompts, comprising:

identifying components parts of a system prompt that is to be played for a caller, wherein said component parts are to be concatenated to form the system prompt;

identifying at least one of said component parts as having digits;

classifying the digits as a time, date or number;

determining a selected locale that is associated with the caller; and

accessing a set of locale-specific rules for the selected locale to determine how to format the digits when they are used in the system prompt.

20. The method of claim 19 further comprising:

classifying a time as a 12-hour time format or a 24-hour time format.

21. The method of claim 19 further comprising:

identifying a date format for the digits.

22. The method of claim 19 further comprising:

identifying a number format for the digits.

23. The method of claim 19 wherein a use of the digits is case sensitive, and the method further comprising:

identifying a case for the digits to be used in the system prompt.

24. The method of claim 19 wherein a use of the digits is gender sensitive, and the method further comprising:

identifying a gender for the digits to be used in the system prompt.

25. The method of claim 19 wherein said component parts comprise prerecorded audio messages.

26. The method of claim 25 wherein said prerecorded audio messages are digital files having a WAV format or an MP3 format.

27. A computer program product having a computer readable medium with computer program logic recorded thereon for use in a system for providing native-sounding text-to-speech conversion, the computer program product comprising:

means for determining a selected locale to be used in converting text to speech;

means for identifying one or more numbers in a text file that is being converted to speech;

means for accessing a set of locale-specific rules associated with the selected locale; and

means for converting the one or more numbers in the text file to speech using the locale-specific rules.

28. The computer program product of claim 27 further comprising:

means for identifying said one or more numbers as a time;

means for identifying said time as having a 12-hour or 24-hour format; and

means for accessing locale-specific time rules to convert said time to speech.

29. The computer program product of claim 27 further comprising:

means for identifying said one or more numbers as a date;

means for identifying a format of said date; and

means for accessing locale-specific date rules to convert said date to speech.

30. The computer program product of claim 27 wherein said one or numbers are case-sensitive for the selected locale;

and

wherein said locale-specific rules further comprise;

means for determining a proper case to be used for said one or more numbers when the one or more numbers are converted to speech.

31. The computer program product of claim 27 wherein said one or more numbers are gender-sensitive for the selected locale;

and

wherein said locale-specific rules further comprise;

means for determining a proper gender to be used for said one or more numbers when the one or more numbers are converted to speech.