Phonetic spelling for speech recognition

• US 6,321,196 B1
• Filed: 07/02/1999
• Issued: 11/20/2001
• Est. Priority Date: 07/02/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Franceschi, Carlos Antonio
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Nolan, Daniel A
• Application Number:
  US09/346,355
• Time in Patent Office: 872 Days
• Field of Search: 704/231, 704/235, 704/270, 704/243, 704/251, 704/244
• US Class Current: 704/243
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering
• CPC Class Codes: G10L 2015/086 Recognition of spelled words

Abstract

Speech recognition apparatus includes means for determining when a speaker desires to spell a first word. The speaker may then say a sequence of words selected from a large vocabulary without being restricted to a pre-specified phonetic alphabet. The apparatus recognizes the spoken words, associates letters with these words and then arranges the letters to form the first word. The speaker may also indicate a desire to stop phonetic spelling. Apparatus may also be used for selecting items from a list.

Claims

1. A speech recognition apparatus, comprising:

means for determining when a speaker gives an indication of a desire to phonetically spell a first word;

means for recognizing a sequence of words selected from a vocabulary and spoken by said speaker after said indication and wherein said vocabulary includes all of the words which said means for recognizing a sequence of words is capable of recognizing at the time said speaker gives said indication;

means for selecting a letter associated with each of said spoken words; and

means for arranging said letters to form said first word.

2. The apparatus of claim 1, wherein said indication is a specific sequence of spoken words.

3. The apparatus of claim 1, wherein said letter is the first letter of each of said words spoken by said speaker after said indication.

4. The apparatus of claim 1, wherein said means for selecting a letter associated with each of said spoken words includes means for selecting a single letter associated with a series of spoken words.

5. The apparatus of claim 4, wherein said series of spoken words comprises a desired letter name, followed by the words, AS IN, or, LIKE IN, and thereafter followed by a word beginning with said desired letter.

6. The apparatus of claim 1, where said means for arranging said letters, arranges said letters in the order that said words spoken by said speaker after said indication are spoken.

7. The apparatus of claim 1, further including means for indicating the end of phonetic spelling.

8. A speech recognition apparatus, comprising:

a display for showing items on a list, each said item having a designated letter;

means for recognizing one or more words selected from a vocabulary and spoken by a speaker and wherein said vocabulary includes all of the words which said means for recognizing a sequence of words is capable of recognizing at the time said speaker gives said indication;

means for selecting a letter associated with each of said one or more words; and

means for selecting said items on said list for which said designated letter matches said letter associated with each of said one or more words.

9. The apparatus of claim 8 wherein a single letter is associated with a series of said words spoken by said speaker.

10. The apparatus of claim 9 wherein said series of spoken words comprises a selected letter mane followed by the words AS IN, or LIKE IN, and thereafter followed by a word beginning with said selected letter.

11. A method for recognizing speech, comprising the steps of:

determining when a speaker gives an indication of a desire to phonetically spell a first word;

utilizing means for recognizing a sequence of words to recognize a sequence of words selected from a vocabulary and spoken by said speaker after said indication and wherein said vocabulary includes all of the words which said means for recognizing a sequence of words is capable of recognizing at the time said speaker gives said indication;

selecting a letter associated with each of said spoken words; and

arranging said letters to form said first word.

12. The method of claim 11, wherein said determining comprises recognizing a specific sequence of spoken words.

13. The method of claim 11, wherein said selecting a letter further comprises selecting the first letter of each of said spoken words.

14. The method of claim 11, wherein said selecting a letter further comprises selecting a single letter associated with a series of spoken words.

15. The method of claim 14, wherein said series of spoken words comprises a desired letter name, followed by the words, AS IN, or, LIKE IN, and thereafter followed by a word beginning with said desired letter.

16. The method of claim 11, wherein said arranging said letters further comprises arranging said letters in the order that said words spoken by said speaker after said indication, are spoken.

17. The method of claim 11, further comprising indicating the end of said phonetic spelling.

18. A method of recognizing speech, comprising the steps of:

displaying items on a list, each said item having a designated letter;

utilizing means for recognizing a sequence of words to recognize one or more words selected from a vocabulary and spoken by a speaker and wherein said vocabulary includes all of the words which said means for recognizing a sequence of words is capable of recognizing at the time said speaker gives said indication;

selecting a letter associated with each of said one or more words; and

selecting said items on said list for which said designated letter matches said letter associated with each of said one or more words.

19. A computer program product for instructing a processor to recognize speech, comprising:

a computer readable medium;

first program instruction means for instructing a processor to determine when a speaker gives an indication of a desire to phonetically spell a first word;

second program instruction means for instructing a processor to recognize a sequence of words selected from a vocabulary and spoken by said speaker after said indication and wherein said vocabulary includes all of the words which said means for instructing a processor to recognize sequence of words is capable of recognizing at the time said speaker gives said indication;

third program instruction means for instructing a processor to select a letter associated with each of said spoken words, and

fourth program instruction means for instructing a processor to arrange said letters to form said first word; and

wherein

said program instruction means are recorded on said medium.

20. The computer program product as set forth in claim 19, wherein said indication is a specific sequence of spoken words.

21. The computer program product as set forth in claim 19, wherein said letter is the first letter of each of said words spoken by said speaker after said indication.

22. The computer program product as set forth in claim 19, wherein said third program instruction means for instructing a processor to select a letter includes instructing a processor to select a single letter associated with a series of spoken words.

23. The computer program product as set forth in claim 19, further comprising:

fifth program instruction means for instructing a processor to recognize the indication of the end of phonetic spelling; and

wherein

said fifth program instruction means is recorded on said medium.

24. A computer program product for instructing a processor to recognize speech, comprising:

a computer readable medium;

first program instruction means for displaying items on a list, each said item having a designated letter;

second program instruction means for recognizing one or more words selected from a vocabulary and spoken by a speaker and wherein said vocabulary includes all of the words which said means for recognizing a sequence of words is capable of recognizing at the time said speaker gives said indication;

third program instruction means for selecting a letter associated with each of said one or more words; and

fourth program instruction means for selecting said items on said list for which said designated letter matches said letter associated with each of said one or more words; and

wherein said program instruction means are recorded on said medium.