Context aware, speech-controlled interface and system
OwnerYangmin Sheninventor
Life of this patent
Estimating the term…
Abstract
A speech-directed user interface system includes at least one speaker for delivering an audio signal to a user and at least one microphone for capturing speech utterances of a user. An interface device interfaces with the speaker and microphone and provides a plurality of audio signals to the speaker to be heard by the user. A control circuit is operably coupled with the interface device and is configured for selecting at least one of the plurality of audio signals as a foreground audio signal for delivery to the user through the speaker. The control circuit is operable for recognizing speech utterances of a user and using the recognized speech utterances to control the selection of the foreground audio signal.
Claims29
A speech-directed user interface system comprising:
- at least one speaker for delivering an audio signal to a user and at least one microphone for capturing speech utterances of a user;
- an interface device for interfacing with the speaker and microphone and providing a plurality of different audio signals to the speaker to be heard by the user;
- a control circuit operably coupled with the interface device and configured for selecting at least one of the plurality of audio signals as a foreground audio signal for delivery to the user through the speaker, the control circuit operable for recognizing speech utterances of a user and using the recognized speech utterances to control the selection of the foreground audio signal.
A method of interfacing with a user with speech comprising:
- delivering an audio signal to the user with at least one speaker and capturing speech utterances of a user with at least one microphone;
- using an interface device for interfacing with the speaker and microphone and providing a plurality of different audio signals to the speaker to be heard by the user;
- selecting, through the interface device, at least one of the plurality of different audio signals as a foreground audio signal for delivery to the user through the speaker.
- recognizing speech utterances of the user and using the recognized speech utterances to control the selection of the foreground audio signal.
Dependencies are inferred from the claim text.