Samsung Electronics Co., Ltd.

Korea University Research and Business Foundation

Neosapience, Inc.

Suwon Shon

Jae-Won Lee

Sung-Soo Kim

Hanseok Ko

Taesu Kim

Younggun Lee

Jinsang Rho

A method for searching content having same voice as a voice of a target speaker from among a plurality of contents includes extracting a feature vector corresponding to the voice of the target speaker, selecting any subset of speakers from a training dataset repeatedly by a predetermined number of times, generating linear discriminant analysis (LDA) transformation matrices using each of the selected any subsets of speakers repeatedly by a predetermined number of times, projecting the extracted speaker feature vector to the selected corresponding subsets of speakers using each of the generated LDA transformation matrices, assigning a value corresponding to nearby speaker class among corresponding subsets of speakers, to each of projection regions of the extracted speaker feature vector, generating a hash value corresponding to the extracted feature vector based on the assigned values, and searching content having a similar hash value to the generated hash value among the contents.

Method for searching for contents having same voice as voice of target speaker, and apparatus for executing same

A method of converting a feature vector includes extracting a feature sequence from an audio signal including utterance of a user; extracting a feature vector from the feature sequence; acquiring a conversion matrix for reducing a dimension of the feature vector, based on a probability value acquired based on different covariance values; and converting the feature vector by using the conversion matrix.

Method and device for transforming feature vector for user recognition

Growing community of inventors

Seoul, South Korea

Suwon Shon