Systems and methods of performing speech recognition using gestures
First Claim
Patent Images
1. A speech recognition method comprising:
- initiating, by a computer system, a state of a computer program;
selecting, by the computer system, a state recognition set based on the state of the computer program;
detecting, by the computer system a gesture of at least one part of a human body;
selecting, by the computer system, a first recognition set based on the gesture, the first recognition set being a subset of the state recognition set;
receiving, by the computer system, a speech input signal; and
recognizing, by the computer system, the speech input signal in the context of the first recognition set, the recognizing resulting in a recognition result.
1 Assignment
0 Petitions
Accused Products
Abstract
Embodiments of the present invention improve methods of performing speech recognition using human gestures. In one embodiment, the present invention includes a speech recognition method comprising detecting a gesture, selecting a first recognition set based on the gesture, receiving a speech input signal, and recognizing the speech input signal in the context of the first recognition set.
14 Citations
23 Claims
-
1. A speech recognition method comprising:
-
initiating, by a computer system, a state of a computer program; selecting, by the computer system, a state recognition set based on the state of the computer program; detecting, by the computer system a gesture of at least one part of a human body; selecting, by the computer system, a first recognition set based on the gesture, the first recognition set being a subset of the state recognition set; receiving, by the computer system, a speech input signal; and recognizing, by the computer system, the speech input signal in the context of the first recognition set, the recognizing resulting in a recognition result. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A speech recognition system comprising:
-
a controller; a gesture detector coupled to provide signals to the controller, the signals corresponding to a gesture; a speech recognizer having access to a plurality of recognition sets, the speech recognizer coupled to provide recognition results to the controller; an audio user interface coupled to receive a speech input and coupled to provide audio signals to the speech recognizer, the audio signals corresponding to the speech input; and a plurality of output devices coupled to the controller, wherein a recognition set is selected from the plurality of recognition sets based on the gesture, wherein the recognition results are generated based on the speech input and the selected recognition set, wherein each recognition set in the plurality of recognition sets is associated with an output device in the plurality of output devices, and wherein the controller provides signals to the output device associated with the selected recognition set, the signals corresponding to the recognition results. - View Dependent Claims (14, 15, 16)
-
-
17. A speech recognition method comprising:
-
initiating, by a computer system, a state of a computer program; selecting, by the computer system, a state recognition set based on the state of the computer program; detecting, by the computer system a gesture of at least one part of a human body; receiving, by the computer system, a speech input signal; and recognizing, by the computer system, the speech input signal in the context of a recognition set, the recognition set being a subset of the state recognition set, the recognizing resulting in a first recognition result; weighting, by the computer system, the first recognition result according to a function associated with the gesture; and determining, by the computer system, a second recognition result based on the weighting. - View Dependent Claims (18, 19, 20, 21, 22)
-
-
23. A system comprising:
-
an automobile; and a speech recognition system in a cabin of said automobile, the speech recognition system comprising, a controller, a gesture detector coupled to provide signals to the controller, the signals corresponding to a gesture, a speech recognizer having access to a plurality of recognition sets, the speech recognizer coupled to provide recognition results to the controller, an audio user interface coupled to receive a speech input and coupled to provide audio signals to the speech recognizer, the audio signals corresponding to the speech input, and a plurality of output devices coupled to the controller, wherein a recognition set is selected from the plurality of recognition sets based on the gesture, wherein the recognition results are generated based on the speech input and the selected recognition set, wherein each recognition set in the plurality of recognition sets is associated with an output device in the plurality of output devices, and wherein the controller provides signals to the output device associated with the selected recognition set, the signals corresponding to the recognition results.
-
Specification