Cisco Technology, Inc.

Tyrone Terry Thorsen

Alan Darryl Gatzke

Todd C Tatum

Shantanu Sarkar

Michael Anthony Ramalho

Paul M Dunn

Laura L Smith

Provided herein are techniques to facilitate controlling audibility of voice commands spoken in a video conference based on eye gaze tracking. A method may include tracking an eye gaze of the participant in relation to voice-enabled user interface objects provided by the video headset and determining that the participant is not an active speaker for the video conference and has an eye gaze towards a particular voice enabled user interface object. Upon the participant speaking a particular voice command associated with the particular voice-enabled user interface object while the participant is not the active speaker for the video conference and has the eye gaze towards the particular voice-enabled user interface object, the method may include inhibiting the particular voice command that is spoken by the participant from being heard by other participants of the video conference.

Controlling audibility of voice commands based on eye gaze tracking

In one implementation, a collaboration server is a conference bridge or other network device configured to host an audio and/or video conference among a plurality of conference participants. The collaboration server sends conference data and a media stream including speech to a speech recognition engine. The conference data may include the conference roster or text extracted from documents or other files shared in the conference. The speech recognition engine updates a default language model according to the conference data and transcribes the speech in the media stream based on the updated language model. In one example, the performance of default language model, the updated language model, or both may be tested using a confidence interval or submitted for approval of the conference participant.

Conference transcription based on conference data

According to certain embodiments, training a transcription system includes accessing recorded voice data of a user from one or more sources. The recorded voice data comprises voice samples. A transcript of the recorded voice data is accessed. The transcript comprises text representing one or more words of each voice sample. The transcript and the recorded voice data are provided to a transcription system to generate a voice profile for the user. The voice profile comprises information used to convert a voice sample to corresponding text.

Training a transcription system

An example method is provided and includes establishing a communication pathway to a building element configured to control at least one environmental setting within a room. The method also includes communicating an ability to control the environmental setting within the room to an endpoint configured to participate in a meeting session. The method further includes receiving a command from the endpoint to adjust the environmental setting during the meeting session. The command can be communicated to the building element. In more specific examples, the method can include registering with one or more application program interfaces (APIs) associated with the building element, and communicating a credential to the building element in order to provide an authentication for controlling the environmental setting. In yet other embodiments, the command to adjust the environmental setting is received via a menu of a user interface provided by a video conferencing platform.

Growing community of inventors

Seattle, WA, United States of America

Tyrone Terry Thorsen