Electronics and Telecommunications Research Institute

Sang-Kwang Lee

Seung-Jae Lee

Jung-Hyun Kim

Yong-Seok Seo

Young-Suk Yoon

Young-Ho Suh

Jee-Hyun Park

Won-Young Yoo

Sung-Min Kim

Jung-Ho Lee

Su-Young Bae

Seung-Jin Hong

Disclosed herein is an apparatus and method for generating a personalized highlight. The apparatus includes memory in which at least one program is recorded and a processor for executing the program. The program may generate respective highlight candidate lists for video data, background sound data, and commentary data separated from game data based on pretrained AI models and generate a highlight reflecting user preferences from a highlight list that is generated based on the generated highlight candidate lists.

Apparatus and method for generating personalized highlight

Disclosed are an apparatus and a method for extracting a highlight section of music. The apparatus for extracting a highlight section of music in accordance with the embodiment of the present invention includes a frame divider that divides an audio file into a plurality of frames having a predetermined sample length; an average energy signal calculator that calculates a signal representing the average magnitude of audio energy for a plurality of samples belonging to each frame for each frame of the plurality of frames; and a highlight section selector that extracts a low frequency signal from the signal representing the average audio energy magnitude for each frame and determines the highlight section from frame sections including maximum points of the low frequency signal.

Apparatus and method for extracting highlight section of music

Disclosed herein is an apparatus and method for measuring quality of audio. The apparatus includes a distorted signal generation unit, an extraction unit, a distortion level measurement unit, a distortion function generation unit, and a search and measurement unit. The distorted signal generation unit generates a plurality of distorted signals with respect to audio in compliance. The extraction unit extracts a fingerprint and AV information corresponding to the audio and fingerprints and AV information corresponding to the plurality of distorted signals. The distortion level measurement unit measures fingerprint distance differences, and arousal and valence (AV) distance differences. The distortion function generation unit generates a fingerprint distortion function and an AV distortion function. The search and measurement unit measures the quality of the audio by extracting a fingerprint and AV information from query audio and then comparing extraction results with the fingerprint distortion function or AV distortion function.

Apparatus and method for measuring quality of audio

The present invention relates generally to a method and apparatus for searching for recommended music using the emotional information of music and, more particularly, to a method and apparatus that enable recommended music to be searched for using mixed emotions by extracting emotional values including a valence value and an arousal value from an input search condition when a predetermined search condition is input by a user, extracting an emotion rank combination corresponding to the extracted emotional value information using an emotion model that includes mixed emotions corresponding to the emotional values, searching a music emotion DB for music information corresponding to the emotion rank combination, and outputting a recommended music list based on the results of the search, thus improving the user's satisfaction with the results of the search.

Method and apparatus for searching for recommended music using emotional information of music

A music search apparatus using an emotion model includes a music database (DB) for storing sound source data about a plurality of pieces of music and Arousal-Valence (AV) coefficients of the respective pieces of music. An emotion model generation unit classifies different emotion types into a plurality of groups, and generates an emotion classification model from using respective probability distributions of the plurality of groups for an AV coefficient plane. A music search unit identifies an emotion type from using information entered by a user when a music search request is received, detects an AV coefficient range for designating an AV coefficient corresponding to the identified emotion type from using the emotion classification model, and searches the music DB for music corresponding to the AV coefficient range.

Growing community of inventors

Daejeon, South Korea

Sang-Kwang Lee