Apparatus and method of video conference to distinguish speaker from participants
AssigneeSamsung Electronics Co., Ltd.
InventorsJun Haeng Lee, Byung Chang Kang, Jong Ho Bang, Keun Joo Park
Life of this patent
Estimating the term…
Abstract
Disclosed are a system and a method that generates image data that represent a speaker to be distinguished, and enables a mobile terminal to provide a video conference service using the image data that distinguishes the speaker. A video conference apparatus may include a speaker distinguishing unit to distinguish, as a speaker, a participant who is speaking from a plurality of participants in the video conference and an image data generating unit to generate image data that represents the distinguished participant differently from other participants.
Claims10
An apparatus for a video conference, the apparatus comprising:
- a speaker distinguishing unit configured to distinguish, as a speaker, a participant who is speaking, from a plurality of participants in the video conference;
- an image data generating unit configured to generate image data that represents the distinguished participant differently from other participants;
- a timbre information storage unit configured to store timbre information associated with at least one participant from among the plurality of participants;
- and
- a timbre information extractor configured to extract speaker timbre information from the voice of the speaker, wherein
- the speaker distinguishing unit is further configured to:
- determine whether timbre information matched to the extracted speaker timbre information is stored in the timbre information storage unit, and
- in response to the matched timbre information not being stored in the timbre information storage unit:
- determine a voice obtaining unit to which the voice of the speaker is inputted;
- and
- distinguish a participant in a location corresponding to the determined voice obtaining unit as the speaker.
A method of video conference, the method comprising:
- storing, in a timbre information storage unit, timbre information associated with at least one participant from among a plurality of participants in the video conference;
- storing location information associated with the at least one participant corresponding to the stored timbre information;
- extracting speaker timbre information of a participant who is speaking among the plurality of participants in the video conference;
- determining whether the extracted speaker timbre information matches timbre information stored in the timbre information storage unit;
- if the extracted speaker timbre information does not match timbre information stored in the timbre information storage unit:
- determining a voice obtaining unit to which the voice of the participant who is speaking is input, and
- determining a participant in a location corresponding to the determined voice obtaining unit as the speaker;
- and
- generating image data that represents the determined speaker participant differently from other participants.
Dependencies are inferred from the claim text.