Systems and methods for speech recognition and separate dialect identification

• US 7,383,182 B2
• Filed: 06/02/2006
• Issued: 06/03/2008
• Est. Priority Date: 07/31/2000
• Status: Expired due to Term

• Current Assignee: Ovonyx Memory Technology, LLC
• Original Assignee: Micron Technology, Inc.
• Inventors: Taylor, George W.
• Primary Examiner(s): Hudspeth; David
• Assistant Examiner(s): SKED, MATTHEW J
• Application Number:
  US11/446,578
• Publication Number:
  US 20070033039A1
• Time in Patent Office: 732 Days
• Field of Search: None
• US Class Current: 704/235
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A speech-to-text conversion system. The two-way speech recognition and dialect system comprises a computer system, an attached microphone assembly, and speech-to-text conversion software. The two-way speech recognition and dialect system includes a database of dialectal characteristics and queries a user to determine their likely dialect. The system uses this determination to reduce the time for the system to reliably transcribe a user'"'"'s speech into text and to anticipate dialectal word usage. In another embodiment of the invention, the two-way speech recognition and dialect system is capable of transcribing the speech of multiple speakers while distinguishing between the different speakers and identifying the text belonging to each speaker.

Claims

1. A method of processing speech for a speech recognition system, the method comprising:

receiving input from a user indicative of at least one dialect parameter;

prior to comparing user speech signals with word data, comparing the at least one dialect parameter to dialect parameter data to determine at least one dialect that the user is likely to have;

receiving speech signals corresponding to spoken words of the user; and

using the at least one dialect that the user is likely to have to produce text representations corresponding to the spoken words of the user.

2. The method of claim 1, wherein the input comprises non-verbal input.

3. The method of claim 2, further comprising receiving the input via a computer peripheral device.

4. The method of claim 3, wherein the computer peripheral device comprises at least one of a mouse, a touch screen and a keyboard.

5. The method of claim 1, further comprising prompting a user to provide the input.

6. The method of claim 5, wherein the user input comprises at least one of the user'"'"'s age, gender, educational level, native language, geographic origin, and current geographic residence.

7. The method of claim 5, wherein said prompting comprises presenting a plurality of queries to the user.

8. The method of claim 1, further comprising accessing a database defining phonemic characteristics associated with the at least one dialect.

9. A system for transcribing spoken words to text, the system comprising:

word data correlating words to speech signals;

dialect parameter data associated with a plurality of dialects; and

a processor configured to receive from a user at least one signal indicative of at least one dialect parameter, the processor being further configured to compare the at least one dialect parameter to the dialect parameter data to determine at least one dialect of the plurality of dialects that the user is likely to have prior to comparing speech signals from the user to the word data.

10. The system of claim 9, wherein the processor is further configured to produce text representations corresponding to the speech signals from the user.

11. The system of claim 9, wherein the processor is further configured to output at least one query signal for prompting the user to provide answer signals indicative of the user'"'"'s dialect.

12. The system of claim 11, further comprising a user interface for communicating the at least one query signal in the form of a screen display.

13. The system of claim 9, wherein the at least one signal indicative of at least one dialect parameter comprises non-verbal input.

14. The system of claim 13, further comprising a computer peripheral device configured to receive the non-verbal input.

15. The system of claim 14, wherein the computer peripheral device comprises at least one of a keyboard, a touch screen and a mouse.

16. The system of claim 9, further comprising a memory configured to store said word data and said dialect parameter data.

17. A speech recognition system comprising:

means for receiving at least one dialect parameter from a user;

means for comparing the at least one dialect parameter to stored dialect parameter data to determine at least one of a plurality of dialects that the user is likely to have prior to receiving speech signals from the user;

means for receiving speech signals corresponding to spoken words of the user; and

means for producing text representations corresponding to the spoken words of the user using the at least one of the plurality of dialects that the user is likely to have.

18. The system of claim 17, further comprising means for storing the dialect parameter data.

19. The system of claim 17, wherein said means for receiving at least one dialect parameter comprises means for receiving non-verbal input from the user.

20. The system of claim 17, further comprising means for prompting the user to provide the at least one dialect parameter.