Graphical user interface and method for modifying pronunciations in text-to-speech and speech recognition systems

• US 7,292,980 B1
• Filed: 04/30/1999
• Issued: 11/06/2007
• Est. Priority Date: 04/30/1999
• Status: Expired due to Fees

• Current Assignee: Nokia of America Corporation (Nokia Corporation)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: McNerney, Michelle, August, Katherine Grace
• Primary Examiner(s): Opsasnick; Michael N.
• Application Number:
  US09/303,057
• Time in Patent Office: 3,112 Days
• Field of Search: 704/270, 704/277, 704/260, 704251-254
• US Class Current: 704/254
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/063 Training

Abstract

A method and user interface which allow users to make decisions about how to pronounce words and parts of words based on audio cues and common words with well known pronunciations. Users input or select words for which they want to set or modify pronunciations. To set the pronunciation of a given letter or letter combination in the word, the user selects the letters and is presented with a list of common words whose pronunciations, or portions thereof, are substantially identical to possible pronunciations of the selected letters. The list of sample, common words is ordered based on frequency of correlation in common usage, the most common being designated as the default sample word, and the user is first presented with a subset of the words in the list which are most likely to be selected. In addition, the present invention allows for storage in the dictionary of several different pronunciations for the same word, to allow for contextual differences and individual preferences.

Claims

1. A method implemented on a computer for allowing a user to set a pronunciation of a string of characters, the method comprising:

storing in a memory device pronunciation data for a plurality of strings of characters to be used by a computing system for pronouncing the strings of characters;

receiving via a user interface a selection by a user of a set of one or more characters in a particular one of the strings of characters;

retrieving from a database accessible by the computer a plurality of sample words representing different possible pronunciations of the selected character set and displaying the retrieved samples;

receiving via a user interface a selection by a user of one of the displayed sample words; and

updating the pronunciation data in said memory device corresponding to the particular string of characters in accordance with a pronunciation of the selected character set in the sample word selected by the user.

2. The method of claim 1, further comprising allowing the user to identify a part of the character string as a separate syllable, and wherein the step of updating the pronunciation data comprises updating data representing the identified separate syllable.

3. The method of claim 1, further comprising allowing the user to identify a part of the character string to associate with an accent, and wherein the step of updating the first pronunciation data comprises updating data representing the identified accent.

4. The method of claim 1, wherein the character string is received as input from the user.

5. The method of claim 1, wherein the character string is selected by the user from a dictionary database accessible to the computer.

6. The method of claim 1 further comprising generating a pronunciation of the character string using the pronunciation represented by the sample word selected by the user as the pronunciation for the selected character set, and audibly outputting the generated pronunciation.

7. The method of claim 6, further comprising allowing the user to select another of the displayed sample words after audibly outputting the generated pronunciation.

8. The method of claim 1, further comprising allowing the user to select a preferred language and wherein the step of retrieving the sample words representing possible pronunciations of the selected character set comprises selecting a database for the preferred language from a plurality of language databases and retrieving the sample words from the selected database.

9. The method of claim 8, further comprising allowing the user to select a second language for the selected character set and retrieving additional sample words from a second database corresponding to the selected second language.

10. The method of claim 1, further comprising allowing the user to select a second of the displayed sample words and storing second pronunciation data comprising the string of characters with the selected character set being assigned the pronunciation represented by the second sample word selected by the user.

11. The method of claim 10, further comprising, during a text-to-speech process of generating audible output of a text file containing the string of characters, selecting one of the first and second pronunciation data.

12. The method of claim 11, further comprising associating the first and second pronunciation data with first and second objects, respectively, and selecting one of the first and second objects, and wherein the step of selecting one of the first and second pronunciation data comprises selecting the pronunciation data associated with the selected object.

13. The method of claim 10, further comprising, during a speech recognition process, recognizing a pronunciation of the string of characters by a user and selecting one of the first and second pronunciation data which most closely matches the recognized pronunciation.

14. The method of claim 13, further comprising associating the first and second pronunciation data with first and second objects, respectively, and selecting one of the first and second objects which is associated with the selected pronunciation data.

15. An article of manufacture comprising a computer readable medium storing program code for, when executed, causing a computer to perform a graphical user interface method for allowing a user to set a pronunciation of a string of characters, the article of manufacture comprising:

program code for storing in a memory device pronunciation data for a plurality of strings of characters to be used by a computing system for pronouncing the strings of characters;

program code for receiving via a user interface a selection by a user of a set of one or more characters in a particular one of the strings of characters;

retrieving from a database accessible by the computer a plurality of sample words representing different possible pronunciations of the selected character set and displaying the retrieved sample words;

program code for receiving via a user interface a selection by a user of one of the displayed sample words; and

updating the pronunciation data in said memory device corresponding to the particular string of characters in accordance with a pronunciation of the selected character set in the sample word selected by the user.

16. The article of claim 15, wherein the program code further causes the computer to generate a pronunciation of the character string using the pronunciation represented by the sample word selected by the user as the pronunciation for the selected character set, and audibly output the generated pronunciation.

17. The article of claim 16, wherein the program code further causes the computer to allow the user to select another of the displayed sample words after audibly outputting the generated pronunciation.

18. The article of claim 15, wherein the program code further causes the computer to allow the user to select a second of the displayed sample words and storing second pronunciation data comprising the string of characters with the selected character set being assigned the pronunciation represented by the second sample word selected by the user.

19. The article of claim 18, wherein the program code further causes the computer, during a text-to-speech process of generating audible output of a text file containing the string of characters, to select one of the first and second pronunciation data.

20. The article of claim 19, wherein the program code further causes the computer to associate the first and second pronunciation data with first and second objects, respectively, and select one of the first and second objects, and wherein the step of selecting one of the first and second pronunciation data comprises selecting the pronunciation data associated with the selected object.

21. The article of claim 18, wherein the program code further causes the computer, during a speech recognition process, to recognize a pronunciation of the string of characters by a user and select one of the first and second pronunciation data which most closely matches the recognized pronunciation.

22. The article of claim 21, wherein the program code further causes the computer to associate the first and second pronunciation files with first and second objects, respectively, and select one of the first and second objects which is associated with the selected pronunciation record.

23. A graphical user interface system for allowing a user to modify a pronunciation of a string of characters, the system comprising:

a dictionary database stored on a memory device comprising a plurality of first character strings and associated pronunciation records;

a pronunciation database stored on a memory device comprising a plurality of second character strings each comprising one or more characters and each associated with a plurality of words, each word having one or more characters which are pronounced in the word in substantially identical fashion to one manner in which the associated second character string may be pronounced;

an input/output system for allowing a user to select one of the first character strings from the dictionary database, to select a set of one or more characters from the selected string, and to select one of the words in the pronunciation database; and

a programmable controller for updating said dictionary database to reflect a pronunciation of the selected first string of characters in accordance with a pronunciation of the selected character set in the selected one of the words.