Hewlett-packard Development Company, L.p.

David A Bryan

Yibo Liu

Stephen C Botzko

Rajen Bhatt

Kui Zhang

Yong Yan

Raghavendra Balavalikar Krishnamurthy

A multi-camera video conference call system is provided with a plurality of cameras connected together over a communication network to generate a corresponding plurality of input frame images taken from different perspectives of a video conference room, where the multi-camera video conference call system detects one or more human heads for any meeting participants captured in the input frame images, generates a head bounding box which surrounds each detected human head, extracts a body bounding box which surrounds the detected human head and at least an upper body portion of a meeting participant belonging to the detected human head, generates a participant identification feature embedding from each body bounding box, and performs person re-identification processing on all generated participant identification feature embeddings to determine a count of the meeting participants in the video conference room.

Assignment of unique identifications to people in multi-camera field of view

A video conference call control system is provided with an audio mixer to receive an audio speech signal at one or more network devices connected to the video conference call; to generate first and second talker identification values from the audio speech signal; to compare the first and second talker identification values during a timing comparison window to determine if the first and second talker identification values are identical and received simultaneously or substantially contemporaneously; and to selectively mute one or more audio devices at the network device(s) if the first and second talker identification values are identical and received simultaneously or substantially contemporaneously so that microphone input signals to the audio mixer are muted to prevent 'playback' echo effects and so that microphone input and audio loudspeaker output signals to the audio mixer are muted to prevent “double join” echo effects.

Speaker identification-based echo detection and solution

Growing community of inventors

Austin, TX, United States of America

David A Bryan