Abstract: A technique for enhancing video representation in network-based meetings dynamically replaces low-quality video feeds with animated avatars. The system evaluates individual video feeds against quality thresholds related to head pose, facial feature visibility, and image clarity. When a feed fails to meet these thresholds, an animation of the participant is generated using a previously captured image. Speech context analysis enables the application of realistic facial expressions and lip movements to the animation. The animated avatar, synchronized with the speech of the participant, is then displayed in place of the original video feed, within the user interface of the network-based meeting. This approach maintains visual engagement for remote participants, even when in-room attendees are partially occluded, poorly captured by the camera, or have suboptimal head poses.

Abstract: The system may determine the size of the SOI from an uncropped, non-zoomed-in image (e.g., a video stream or static image). Based upon the size of the image, the system can determine the optimal resolution for each SOI video stream. This approach minimizes the need for upscaling and downscaling operations, thereby preserving video quality and reducing bandwidth usage.

Abstract: The disclosure herein describes providing responses to natural language queries associated with transcripts at least by searching multiple indexes. A transcript associated with a communication among a plurality of speakers is obtained, wherein sets of artifact sections are identified in the transcript. A set of section indexes is generated from the transcript based on artifact type definitions. A natural language query associated with the transcript is analyzed using a natural language model and query metadata of the analyzed natural language query is obtained. At least one section index of the set of section indexes is selected based on the obtained query metadata and that selected at least one section index is searched. A response to the natural language query is provided including result data from the searched at least one search index, wherein the result data includes a reference to an artifact section referenced by the searched section index(es).

Abstract: Techniques for generating a gallery view of tiles for in-area participants who are participating in an online meeting are disclosed. A video stream is accessed, where this stream includes an area view of an area in which an in-area participant is located. This area view comprises pixels representative of the area and pixels representative of the in-area participant. The pixels representative of the in-area participant are identified. A field of view of the in-area participant is generated. A tile of the in-area participant is generated based on the field of view. This tile is then displayed while the area view is not displayed.

Abstract: A method for facilitating a remote conference includes receiving a digital video and a computer-readable audio signal. A face recognition machine is operated to recognize a face of a first conference participant in the digital video, and a speech recognition machine is operated to translate the computer-readable audio signal into a first text. An attribution machine attributes the text to the first conference participant. A second computer-readable audio signal is processed similarly, to obtain a second text attributed to a second conference participant. A transcription machine automatically creates a transcript including the first text attributed to the first conference participant and the second text attributed to the second conference participant.

Abstract: The disclosure herein describes providing responses to natural language queries associated with transcripts at least by searching multiple indexes. A transcript associated with a communication among a plurality of speakers is obtained, wherein sets of artifact sections are identified in the transcript. A set of section indexes is generated from the transcript based on artifact type definitions. A natural language query associated with the transcript is analyzed using a natural language model and query metadata of the analyzed natural language query is obtained. At least one section index of the set of section indexes is selected based on the obtained query metadata and that selected at least one section index is searched. A response to the natural language query is provided including result data from the searched at least one search index, wherein the result data includes a reference to an artifact section referenced by the searched section index(es).

Abstract: A method for facilitating a remote conference includes receiving a digital video and a computer-readable audio signal. A face recognition machine is operated to recognize a face of a first conference participant in the digital video, and a speech recognition machine is operated to translate the computer-readable audio signal into a first text. An attribution machine attributes the text to the first conference participant. A second computer-readable audio signal is processed similarly, to obtain a second text attributed to a second conference participant. A transcription machine automatically creates a transcript including the first text attributed to the first conference participant and the second text attributed to the second conference participant.

Abstract: The disclosure herein describes providing responses to natural language queries associated with transcripts at least by searching multiple indexes. A transcript associated with a communication among a plurality of speakers is obtained, wherein sets of artifact sections are identified in the transcript. A set of section indexes is generated from the transcript based on artifact type definitions. A natural language query associated with the transcript is analyzed using a natural language model and query metadata of the analyzed natural language query is obtained. At least one section index of the set of section indexes is selected based on the obtained query metadata and that selected section index is searched. A response to the natural language query is provided including result data from the searched at least one search index, wherein the result data includes a reference to an artifact section referenced by the searched section index(es).

Abstract: The disclosure herein describes providing responses to natural language queries associated with transcripts at least by searching multiple indexes. A transcript associated with a communication among a plurality of speakers is obtained, wherein sets of artifact sections are identified in the transcript. A set of section indexes is generated from the transcript based on artifact type definitions. A natural language query associated with the transcript is analyzed using a natural language model and query metadata of the analyzed natural language query is obtained. At least one section index of the set of section indexes is selected based on the obtained query metadata and that selected at least one section index is searched. A response to the natural language query is provided including result data from the searched at least one search index, wherein the result data includes a reference to an artifact section referenced by the searched section index(es).

Abstract: A method for facilitating a remote conference includes receiving a digital video and a computer-readable audio signal. A face recognition machine is operated to recognize a face of a first conference participant in the digital video, and a speech recognition machine is operated to translate the computer-readable audio signal into a first text. An attribution machine attributes the text to the first conference participant. A second computer-readable audio signal is processed similarly, to obtain a second text attributed to a second conference participant. A transcription machine automatically creates a transcript including the first text attributed to the first conference participant and the second text attributed to the second conference participant.

Abstract: A method for facilitating a remote conference includes receiving a digital video and a computer-readable audio signal. A face recognition machine is operated to recognize a face of a first conference participant in the digital video, and a speech recognition machine is operated to translate the computer-readable audio signal into a first text. An attribution machine attributes the text to the first conference participant. A second computer-readable audio signal is processed similarly, to obtain a second text attributed to a second conference participant. A transcription machine automatically creates a transcript including the first text attributed to the first conference participant and the second text attributed to the second conference participant.

Abstract: A method for facilitating a remote conference includes receiving a digital video and a computer-readable audio signal. A face recognition machine is operated to recognize a face of a first conference participant in the digital video, and a speech recognition machine is operated to translate the computer-readable audio signal into a first text. An attribution machine attributes the text to the first conference participant. A second computer-readable audio signal is processed similarly, to obtain a second text attributed to a second conference participant. A transcription machine automatically creates a transcript including the first text attributed to the first conference participant and the second text attributed to the second conference participant.

Abstract: In one embodiment, a computing system generates a reference distance to classify a user in a first position or a second position and measures a current distance of the user using a camera. The current distance measured using features of the user and the current distance is not a measurement of distance of the user to the camera. The computing system determines that the user is in one of the first position and the second position based on comparing the reference distance to the current distance. A user interface operates in a first mode when the user is in the first position and operates in a second mode when the user is in the second position.