Domain-specific concatenative audio

• US 7,334,183 B2
• Filed: 05/29/2003
• Issued: 02/19/2008
• Est. Priority Date: 01/14/2003
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Rusnak, Christopher, Bass, Joshua, Breitenbach, Stephen
• Primary Examiner(s): DESAI, RACHNA SINGH
• Application Number:
  US10/449,207
• Publication Number:
  US 20040138887A1
• Time in Patent Office: 1,727 Days
• Field of Search: 715/500.1, 715/536, 715/531, 742/60, 742/51
• US Class Current: 715/201
• CPC Class Codes: G06F 9/454 Multi-language systems; Localisation; Internationalisation
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: H04M 2203/2061 Language aspects
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

One embodiment of the present invention provides a system for generating speech output from a text string. During operation, the system first receives the text string and then examines the text string to locate one or more substrings within the text string that are found in a speech library. Next, the system looks up speech files associated with the one or more substrings in the speech library. The system then concatenates these speech files to produce a speech output for a user.

Claims

1. A method for generating speech output of a text string, comprising:

receiving the text string comprised of more than one word and storing the text string in a remaining string buffer holding an unmatched portion of the string;

recursively repeating the following operations until the length of the text string in the remaining string buffer is not greater than zero;

initializing a working copy of the text string from the remaining string buffer,

comparing the working copy of the text string with strings in a speech library,

removing a rightmost word from the working copy until the working copy of the text string matches a string in the speech library or until the length of the working copy of the text string is one,

determining whether the length of the working copy of the text string is one and whether it matches a string in the speech library,

when the length of the working copy of the text string is one and does not match a string in the speech library, removing the leftmost word from the text string in the remaining string buffer and converting the leftmost word into a sound file using a text to speech converter,

when the working copy of the text string matches a string in the speech library, looking up an associated speech file for the text string in the speech library, and

removing the matched text from the text string in the remaining string buffer;

subsequent to the recursive operations, concatenating the speech files and any sound files together to produce a speech output for a user.

2. The method of claim 1, wherein the speech library includes phrases related to a specific domain.

3. The method of claim 1, wherein a text string can include a complete sentence.

4. The method of claim 1, wherein a text string can include a phrase.

5. The method of claim 1, wherein the concatenative audio files provide proper inflection for the speech output.

6. The method of claim 1, further comprising expanding numbers, dates, and times while producing the speech output.

7. The method of claim 1, wherein the speech library can include locale-specific speech files for multiple languages and locales.

8. The method of claim 7, wherein a locale-specific speech file is spoken in a locale-specific version of a language.

9. A computer-readable storage device storing instructions that when executed by a computer cause the computer to perform a method for generating speech output of a text string, the method comprising:

receiving the text string comprised of more than one word and storing the text string in a remaining string buffer holding an unmatched portion of the string;

recursively repeating the following operations until the length of the text string in the remaining string buffer is not greater than zero;

initializing a working copy of the text string from the remaining string buffer,

comparing the working copy of the text string with strings in a speech library,

removing a rightmost word from the working copy until the working copy of the text string matches a string in the speech library or until the length of the working copy of the text string is one,

determining whether the length of the working copy of the text string is one and whether it matches a string in the speech library,

when the length of the working copy of the text string is one and does not match a string in the speech library, removing the leftmost word from the text string in the remaining string buffer and converting the leftmost word into a sound file using a text to speech converter,

when the working copy of the text string matches a string in the speech library, looking up an associated speech file for the text string in the speech library, and

removing the matched text from the text string in the remaining string buffer;

subsequent to the recursive operations, concatenating the speech files and any sound files together to produce a speech output for a user.

10. The computer-readable storage device of claim 9, wherein the speech library includes phrases related to a specific domain.

11. The computer-readable storage device of claim 9, wherein a text string can include a complete sentence.

12. The computer-readable storage device of claim 9, wherein a text string can include a phrase.

13. The computer-readable storage device of claim 9, wherein the concatenative audio files provide proper inflection for the speech output.

14. The computer-readable storage device of claim 9, the method further comprising expanding numbers, dates, and times while producing the speech output.

15. The computer-readable storage device of claim 9, wherein the speech library can include locale-specific speech files for multiple languages and locales.

16. The computer-readable storage device of claim 15, wherein a locale-specific speech file is spoken in a locale-specific version of a language.

17. An apparatus for generating speech output of a text string, comprising:

a processor;

a receiving mechanism configured to;

receive the text string comprised of more than one word and store the text string in a remaining string buffer holding an unmatched portion of the string;

recursively repeating the following operations until the length of the text string in the remaining string buffer is not greater than zero;

the receiving mechanism configured to initialize a working copy of the text string from the remaining string buffer,

an examining mechanism configured to compare the working copy of the text string with strings in a speech library,

an examining mechanism configured to remove a rightmost word from the working cony until the working copy of the text string matches a string in the speech library or until the length of the working copy of the text string is one,

an examining mechanism configured to determine whether the length of the working copy of the text string is one and whether it matches a string in the speech library,

an examining mechanism configured to remove the leftmost word from the text string in the remaining string buffer and convert the leftmost word into a sound file using a text to speech converter when the length of the working copy of the text string is one and does not match a string in the speech library,

a lookup mechanism configured to look up an associated speech file for the text string in the speech library when the examining mechanism determines the working copy of the text string matches a string in the speech library, and

removing the matched text from the text string in the remaining string buffer;

subsequent to the recursive operations, a concatenating mechanism is configured to concatenate the speech files and any sound files together to produce a speech output for the user.

18. The apparatus of claim 17, wherein the speech library includes phrases related to a specific domain.

19. The apparatus of claim 17, wherein a text string can include a complete sentence.

20. The apparatus of claim 17, wherein a text string can include a single word.

21. The apparatus of claim 17, wherein the concatenative audio files provide proper inflection for the speech output.

22. The apparatus of claim 17, further comprising an expanding mechanism configured to expand numbers, dates, and times while producing the speech output.

23. The apparatus of claim 17, wherein the speech library can include locale-specific speech files for multiple languages and locales.

24. The apparatus of claim 23, wherein a locale-specific speech file is spoken in a locale-specific version of a language.