Regularized Attention based Deep Learning Algorithm for Polyphonic Sound Event Detection

Deep Feature Embedding via Part-aligned Multi-view LSTM Architecture for Person Re-identification

Generalized Two-Filter Smoothing for Melody Extraction

Music Analysis and Clustering via Discovering Latent Musical Hierarchy Structure and Components Based on a Topic Model

Non-parametric Model Based Speech Synthesis

On normalized spectral subband moments

3축 가속도계를 이용한 은닉 마르코프 모델 기반의 행동인식

ν-Structured 서포트 벡터 머신을 이용한 음성 인식기 훈련

심리음향적 제약조건 최적화에 기반한 잡음 제거 기법