Speech to text method and system

• US 20020133342A1
• Filed: 03/18/2002
• Published: 09/19/2002
• Est. Priority Date: 03/16/2001
• Status: Abandoned Application

• Current Assignee: Jennifer Mckenna
• Original Assignee: Jennifer Mckenna
• Inventors: McKenna, Jennifer
• Application Number:
  US10/100,744
• Publication Number:
  US 20020133342A1
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence

Abstract

The present invention is an automated dictation method and system for converting speech to text. The invention includes a voice manipulation system for converting a speech signal that is based on spoken words to a standardized signal and a dictation system for generating a textual representation of the spoken words using the standardized signal.

Claims

1. A speech to text conversion system comprising:

a voice manipulation system for standardizing a speech signal, said speech signal corresponding to spoken words; and

a dictation system for generating a textual representation of said spoken words based on said standardized signal.

2. The system of claim 1, further comprising:

a microphone for developing said speech signal from said spoken words.

3. The system of claim 2, wherein said microphone comprises at least a transmitter and said voice manipulation system comprises at least a receiver, said microphone transmitting said speech signal using said transmitter for receipt at said voice manipulation system through said receiver.

4. The system of claim 1, further comprising:

a storage device.

5. The system of claim 4, wherein said storage device is configured to store said speech signal.

6. The system of claim 4, wherein said storage device is configured to store said standardized signal.

7. The system of claim 1, further comprising:

an output device for presenting said textual representation.

8. The system of claim 7, wherein said output device is a monitor operatively associated with said dictation system for displaying text corresponding to said textual representation.

9. The system of claim 7, wherein said output device is a printer operatively associated with said dictation system for printing text corresponding to said textual representation.

10. The system of claim 9, wherein said printer is a braille printer.

11. A method for converting speech to text comprising the steps of:

standardizing a speech signal, said speech signal corresponding to spoken words; and

generating a textual representation of said spoken words based on said standardized signal.

12. The method of claim 11, further comprising:

storing said standardized signal for use in said generating step.

13. The method of claim 11, further comprising:

storing said speech signal for use during said standardizing step.

14. The method of claim 11, wherein said standardizing step comprises at least the step of:

manipulating said speech signal such that after standardization the signal will be essentially equivalent for said spoken words regardless of speaker.

15. The method of claim 11, further comprising:

presenting text corresponding to said textual representation.

16. The method of claim 15, wherein said presenting step comprises at least displaying said text on a monitor.

17. The method of claim 15, wherein said presenting step comprises at least printing said text.

18. A computer program product for speech to text conversion, said computer program product comprising:

computer readable program code embodied in a computer readable medium, the computer readable program code comprising at least;

computer readable program code for standardizing a speech signal, said speech signal corresponding to spoken words; and

computer readable program code for generating a textual representation of said spoken words based on said standardized signal.

19. A system for speech to text conversion, said system comprising:

means for standardizing a speech signal, said speech signal corresponding to spoken words; and

means for generating a textual representation of said spoken words based on said standardized signal.