Abstract: A system for audio-visual multi-speaker speech separation. The system includes a processing circuitry and a memory containing instructions that, when executed by the processing circuitry, configure the system to: receive audio signals captured by at least one microphone; receive video signals captured by at least one camera; and apply audio-visual separation on the received audio signals and video signals to provide isolation of sounds from individual sources, wherein the audio-visual separation is based, in part, on angle positions of at least one speaker relative to the at least one camera. The system provides for reliable speech processing and separation in noisy environments and environments with multiple users.

Abstract: A voice-controlled device, comprising at least one hardware processor adapted for receiving a set of preferred local commands or computing thereof by receiving from at least one other voice-controlled device a set of used commands and identifying in a plurality of voice commands a set of preferred local commands not members of the set of used commands; and responding to at least one voice command, received from a user, subject to identifying the at least one voice command in the set of preferred local commands, otherwise declining to respond thereto.

Abstract: A system and method for audio-visual multi-speaker speech separation, including: receiving audio signals captured by at least one microphone; receiving video signals captured by at least one camera; and applying audio-visual separation on the received audio signals and video signals to provide isolation of sounds from individual sources, wherein the audio-visual separation is based, in part, on angle positions of at least one speaker relative to the at least one camera.

Abstract: Method and apparatus to minimize computation in real time photo realistic rendering for efficiently creating, in real time, personalized videos that include personal images and personal text and targeted advertising arts according to viewer profiles. The method and apparatus for automatically and photo realistically embedding artwork onto video content generally includes a container implanter that creates generic 2D containers for an image artwork, which includes instructions for embedding the artwork, automatically and photo realistically, onto video content, and a renderer or network renderer that automatically and photo realistically embeds the artwork onto video content.

Abstract: An apparatus and method for embedding artwork into a video in several phases. Initially, a segment suitable for artwork placement is identified and marked within an original video, and a container is implanted therein to determine the appropriate position and video transformations for future artwork objects. Then, an artwork provider experiments with sending artwork for each container and viewing that artwork placed within the video, until the current artwork is approved for placement. Finally, a final version, which includes the selected artwork embedded within the original video, is rendered, adapted for a distributor, and the end product is distributed and viewed conventionally. The container implantation is relatively labor intensive and therefore expensive, but costs are subsequently distributed over many sessions of different artwork placements within the same container. Typical applications are in advertising, art and fun.

Abstract: A method and system for preparing a video advertising insertion clip that utilizes an existing video presentation that currently features and/or will feature virtual product placement. The advertising insertion clip is obtained with minimal additional production resources and overhead in conjunction with a virtual product placement process. By the use of scripts, metadata, and/or equivalent machine-readable instructions or commands, the process can be configured to automatically generate insertion clips for video presentations that are repurposed and/or to be repurposed.