Samsung Electronics Co., Ltd.

Industry-university Cooperation Foundation Hanyang University

Geeyeun Kim

Hangil Moon

Jaemo Yang

Kyoungho Bang

Seonmi Kim

Jaeseong Lee

Sangeun Kim

Junwoo Cha

Jeonghwan Choi

Joonhyuk Chang

Dail Kim

Yungyeo Kim

Minsang Baek

Wongook Choi

A method for separating a target sound source, includes: obtaining a mixed sound source including at least one sound source; obtaining, based on the mixed sound source, scene information related to the mixed sound source; converting, based on the scene information, a first embedding vector corresponding to a designated sound source group into a second embedding vector; and separating, based on the mixed sound source and the second embedding vector, the target sound source from the mixed sound source.

Method for separating target sound source from mixed sound source and electronic device thereof

Electronic devices and methods of use include a plurality of microphones, a speaker, an audio module, and a processor electrically coupled to the plurality of microphones, the speaker, and the audio module. The processor may be configured to control the audio module to separate each of input signals of ambient sounds input respectively through the plurality of microphones into a plurality of frequency bands by frequency conversion, control the audio module to obtain a gain value for each of the plurality of frequency bands based on an inter-channel phase variance for the plurality of frequency bands, control the audio module to filter a first frequency band signal with a directionality based on the gain value for each of the plurality of frequency bands, and control the speaker to output an output signal processed based on the first frequency band signal.

Electronic device and method for outputting sound

An electronic device is provided. In order to process an ambient sound according to an audio scene, the electronic device receive an ambient sound, determine an audio scene based on the ambient sound, determine a target signal processing profile corresponding to the audio scene among one or more signal processing profile, and process the ambient sound according to the target signal processing profile.

Electronic device for controlling ambient sound based on audio scene and operating method thereof

Growing community of inventors

Suwon-si, South Korea

Geeyeun Kim