발행물

전체 논문

124

11

Gated Recurrent Context: Softmax-Free Attention for Online Encoder-Decoder Speech Recognition
김남수, 이현승, 강우현, 천성준, 김형주
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 202101

12

Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-Supervised Speaker Verification
Mun Sung Hwan, 김남수, Han Min Hyun, Lee Dongjune, Kim Jihwan
IEEE ACCESS, 202101

13

Gated Recurrent Attention for Multi-Style Speech Synthesis
김남수, 천성준, 이준엽, 최병진, 이현승
APPLIED SCIENCES-BASEL, 202008

14

Disentangled Speaker and Nuisance Attribute Embedding for Robust Speaker Verification
강우현, 김남수, 문성환, 한민현
IEEE ACCESS, 202007

15

Memory Attention: Robust Alignment Using Gating Mechanism for End-to-End Speech Synthesis
이준엽, 김남수, 천성준, 최병진
IEEE SIGNAL PROCESSING LETTERS, 202001

16

Adversarially Learned Total Variability Embedding for Speaker Recognition with Random Digit Strings
김남수, 강우현
SENSORS, 201908

17

Disentangled feature learning for noise-invariant speech enhancement
배수현, 김남수, 최인규
APPLIED SCIENCES-BASEL, 201906

18

Deep convolutional neural network with structured prediction for weakly supervised audio event detection
김남수, 최인규, 배수현
APPLIED SCIENCES-BASEL, 201906

19

Unsupervised learning of total variability embedding for speaker verification with random digit strings
강우현, 김남수
APPLIED SCIENCES-BASEL, 201904

20

DNN-based monaural speech enhancement with temporal and spectral variations equalization
김남수, T. G. Kang, J. W. Shin
DIGITAL SIGNAL PROCESSING, 201812