Computer-implemented speech recognition system training
First Claim
Patent Images
1. A method for training a computer implemented speech recognition system, comprising:
- (a) displaying an icon representing a concept;
(b) prompting a user to generate a vocalization comprising any sound determined by the user to associate to the icon;
(c) confirming association of the vocalization with the icon; and
(d) saving the association of the vocalization with the icon to a computer readable medium.
2 Assignments
0 Petitions
Accused Products
Abstract
Computer-implemented speech recognition system training including displaying an icon representing a concept, prompting a user to generate a vocalization comprising any sound determined by the user to associate to the icon, confirming association of the vocalization with the icon, and saving the association of the vocalization with the icon to a computer readable medium. The invention has particular applicability, but is not limited, to the field of vehicle diagnostics including vehicle wheel alignment or vehicle engine diagnostics.
214 Citations
20 Claims
-
1. A method for training a computer implemented speech recognition system, comprising:
-
(a) displaying an icon representing a concept;
(b) prompting a user to generate a vocalization comprising any sound determined by the user to associate to the icon;
(c) confirming association of the vocalization with the icon; and
(d) saving the association of the vocalization with the icon to a computer readable medium. - View Dependent Claims (2, 3, 4, 5, 6)
prompting a user to repeat the vocalization.
-
-
5. A method for training a computer implemented speech recognition system according to claim 4, further comprising:
-
(e) prompting a user to repeat a vocalization associated with the icon;
(f) comparing the repeated vocalization with a plurality of stored vocalizations to identify an associated icon; and
(g) displaying an identified icon.
-
-
6. A method for training a computer implemented speech recognition system according to claim 1, wherein the vocalization is a word or a plurality of words.
-
7. A computer-readable medium bearing instructions enabling a computer having at least one processor to associate a sound made by a user to a concept associated with a selected icon, the instructions, when executed by a computer, causing the computer to carry out the steps of:
-
relating a sound made by a user to a concept associated with a selected icon; and
storing the sound made by the user as well as the relationship between the stored sound and the concept associated with the selected icon, wherein the sound made by the user may include any sound or combination of sounds. - View Dependent Claims (8, 9, 10)
comparing a subsequent sound made by the user to the stored sound to determine if the subsequent sound corresponds to the stored sound; and
identifying the concept related to the stored sound based upon the correspondence between the stored sound and the subsequent sound.
-
-
9. A computer-readable medium bearing instructions according to claim 8, wherein the instructions are further arranged to cause the computer to perform the step of:
executing an instruction set corresponding to the concept related to the stored user vocalization.
-
10. A computer-readable medium bearing instructions according to claim 7, wherein the instructions are further arranged to cause the computer to perform the step of:
-
outputting a control signal to a device connected to the computer, wherein the device changes from a first state to a second state as a result of the control signal.
-
-
11. A vehicle diagnostics system comprising:
-
a computer having at least one processor;
a sound-to-signal transducer configured to output a signal to the processor corresponding to a sound input to the sound-to-signal transducer;
a display configured to receive signals from the processor and display images corresponding to the received signals; and
a speech recognition program product configured to process, in combination with the processor, a signal provided to the processor by the sound-to-signal transducer, wherein the speech recognition program product includes instructions relating a concept represented by an icon displayed on the display to any sound determined by the user. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19, 20)
a device configured to be controlled by the computer, and wherein the control signal output by the speech recognition program product is used by the processor to change a state of the device from a first state to a second state.
-
-
18. A vehicle diagnostics system comprising according to claim 17, wherein the device is at least one of a lift and a jack configured to move up or down in response to a signal output by the computer.
-
19. A vehicle diagnostics system comprising according to claim 13, a sensor for measuring a vehicle parameter of interest and providing a signal corresponding to the measured parameter of interest to the processor.
-
20. A vehicle diagnostics system comprising according to claim 12, wherein the icon represents a concept related to vehicle engine diagnostics.
Specification