발행물

전체 논문

124

1

Variable-Length Speaker Conditioning in Flow-Based Text-to-Speech
김남수, Choi Byoung Jin, Jeong Myeonghun, Kim Minchan
IEEE SIGNAL PROCESSING LETTERS, 202401

2

Transfer Learning for Low-Resource, Multi-Lingual, and Zero-Shot Multi-Speaker Text-to-Speech
Jeong Myeonghun, Kim Minchan, 김남수, Choi Byoung Jin, Yoon Jaesam, Jang Won
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 202401

3

Efficient Parallel Audio Generation Using Group Masked Language Modeling
Jeong Myeonghun, 김남수, Kim Minchan, Lee Joun Yeop
IEEE SIGNAL PROCESSING LETTERS, 202401

4

Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models
김남수, Yoon Ji Won, Kim Hyung Yong, Lee Hyeonseung, Ahn Sunghwan, Kim Nam Soo
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 202301

5

SNAC: Speaker-Normalized Affine Coupling Layer in Flow-Based Architecture for Zero-Shot Multi-Speaker Text-to-Speech
Choi Byoung Jin, 김남수, Jeong Myeonghun, Lee Joun Yeop
IEEE SIGNAL PROCESSING LETTERS, 202201

6

A Controllable Multi-Lingual Multi-Speaker Multi-Style Text-to-Speech Synthesis With Multivariate Information Minimization
김남수, Cheon Sung Jun, Choi Byoung Jin, Kim Minchan, Lee Hyeonseung
IEEE SIGNAL PROCESSING LETTERS, 202201

7

Neurally Optimized Decoder for Low Bitrate Speech Codec
김남수, Kim Hyung Yong, Yoon Ji Won, Cho Won Ik
IEEE SIGNAL PROCESSING LETTERS, 202201

8

Chiral symmetry and taste symmetry from the eigenvalue spectrum of staggered Dirac operators
김남수, 이원종, Hwancheol Jeong, Chulwoo Jung, Seungyeob Jwa, Jangho Kim, Jeehun Kim, Sunghee Kim, Sunkyu Lee, Youngjo Lee, Jeonghwan Pak
PHYSICAL REVIEW D, 202107

9

TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition
김남수, 이현승, 김형용, 조원익, 윤지원
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 202104

10

A Multi-Resolution Approach to GAN-Based Speech Enhancement
김남수, 윤지원, 천성준, 강우현, 김형용
APPLIED SCIENCES-BASEL, 202101