Two-way speech recognition and dialect system

• US 20040215456A1
• Filed: 05/24/2004
• Published: 10/28/2004
• Est. Priority Date: 07/31/2000
• Status: Active Grant

• Current Assignee: Ovonyx Memory Technology, LLC (Micron Technology, Inc.)
• Original Assignee: George W. Taylor
• Inventors: Taylor, George W.
• Granted Patent: US 7,155,391 B2
• Time in Patent Office: Days
• 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 system for transcribing spoken words to text, the system comprising:

at least one data structure containing word data correlating text representations of words to speech signals, wherein the at least one data structure includes dialect parameter data that can be used to recognize selected dialects corresponding to selected users; and

a processor configured to receive speech signals, wherein the processor compares the speech signals to the word data in the at least one data structure to produce text representations corresponding to spoken words, wherein the processor initially sends signals to the user asking the user at least one question indicative of the user'"'"'s dialect to thereby induce the user to provide answer signals to the processor that are indicative of dialect parameters, and wherein the processor compares the dialect parameters from the user to the dialect parameter data in the at least one data structure to determine a dialect corresponding to the user prior to comparing the speech signals to the word data in the at least one data structure to produce text representations corresponding to the spoken words.

2. The system of claim 1, wherein the at least one data structure includes phonemic characteristic data.

3. The system of claim 1, wherein the dialect parameters include at least one parameter indicative of a physical characteristic of the user.

4. The system of claim 3, wherein the physical characteristic comprises the user'"'"'s age.

5. The system of claim 1, wherein the dialect parameters include at least one parameter indicative of the geographic origin of the user.

6. The system of claim 1, wherein the dialect parameters include at least one parameter indicative of the educational level of the user.

7. A speech recognition system comprising:

dialect data; and

processor circuitry configured to convert speech signals into text representations, wherein the processor circuitry receives at least one dialect parameter, and wherein the processor circuitry compares the at least one dialect parameter to the dialect data to determine a dialect corresponding to a user.

8. The speech recognition system of claim 7, wherein the processor circuitry uses the determined dialect to produce text representations corresponding to spoken words of the user.

9. The speech recognition system of claim 8, further comprising word data correlating text representations of words to speech signals.

10. The speech recognition system of claim 9, wherein the processor circuitry determines the dialect corresponding to the user prior to comparing the speech signals to the word data to produce text representations corresponding to spoken words of the user.

11. The speech recognition system of claim 7, wherein the processor circuitry sends a first signal to the user so as to thereby induce the user to provide to the processor circuitry an answer signal that is indicative of the at least one dialect parameter.

12. The speech recognition system of claim 7, further comprising a memory configured to store the dialect data and the word data.

13. A method of translating spoken words into corresponding text, the method comprising:

receiving at least one dialect parameter; and

comparing the at least one dialect parameter to dialect data to determine a dialect corresponding to a user; and

using the determined dialect to produce text representations corresponding to spoken words of the user.

14. The method of claim 13, wherein said acts of receiving and comparing are performed by a processor.

15. The method of claim 13, wherein said act of comparing occurs prior to producing the text representations corresponding to the spoken words of the user.

16. The method of claim 13, wherein the dialect data is stored in a memory.

17. The method of claim 13, additionally comprising sending a signal to the user so as to thereby induce the user to provide an answer signal that is indicative of the at least one dialect parameter.

18. A speech recognition system comprising:

a means for storing dialect data; and

a means for processing speech signals into text representations, wherein the processing means receives at least one dialect parameter, and wherein the processing means compares the at least one dialect parameter to the dialect data to determine a dialect corresponding to a user.

19. The speech recognition system of claim 18, wherein the storing means also stores word data correlating text representations of words to speech signals.

20. The speech recognition system of claim 18, further comprising a means for obtaining input from the user, wherein the processing means receives the at least one dialect parameter via the obtaining means.

21. The speech recognition system of claim 20, wherein the means for obtaining input comprises a keyboard.

22. The speech recognition system of claim 18, further comprising an interface means for sending signals to the user.

23. The speech recognition system of claim 22, wherein the interface means comprises a monitor.

24. The speech recognition system of claim 22, wherein the processing means sends a first signal to the user via the interface means to thereby induce the user to provide an answer signal that is indicative of the at least one dialect parameter.

25. A speech processor for transcribing spoken words to text, wherein the speech processor is configured to send a first signal to a user to thereby induce the user to provide an answer signal that is indicative of at least one dialect parameter, and wherein the speech processor is configured to compare the at least one dialect parameter with stored dialect parameter data so as to determine a dialect corresponding to the user prior to producing text representations corresponding to spoken words of the user.

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

a means for storing word data correlating text representations of words to speech signals and for storing dialect parameter data; and

a means for processing speech signals, wherein the processing means sends a first signal to a user to thereby prompt the user to provide an answer signal that is indicative of at least one dialect parameter, and wherein the processing means compares the at least one dialect parameter to the dialect parameter data to determine a dialect corresponding to the user prior to converting received speech signals into corresponding text signals.

27. A machine loadable software program adapted to control the operation of a processor such that the processor translates audio word signals into corresponding text signals, wherein the software program induces the processor to determine a speaker'"'"'s dialect from at least one dialect parameter prior to translating the audio word signals into corresponding text signals.

28. The software program of claim 27, wherein the software program additionally induces the processor to output a first signal to prompt a speaker to provide an answer signal indicative of the at least one dialect parameter.

29. The software program of claim 27, wherein the software program induces the processor to determine dialects of multiple speakers prior to translating the audio word signals into corresponding text signals.