발행물

전체 논문

388

1

Adaptive splitting mean online expectation-maximization method-based moving object localization
장준혁
DIGITAL SIGNAL PROCESSING, 202504

2

Quad-Net: Melspectrogram vocoder with convolutional layers restricted by the quadrature mirror filter for perfect reconstruction
장준혁
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 202504

3

Few-shot keyword-incremental learning using compositional information
장준혁
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 202504

4

Diffusion-based target device style transfer for robust acoustic scene classification
장준혁
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 202504

5

Multimodal emotion recognition with target speaker-based facial embeddings
장준혁
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 202504

6

Trainable adaptive score normalization for automatic speaker verification
장준혁
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 202504

7

Progressive subband modeling for artifacts-free speech super-resolution
장준혁
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 202504

8

Flow-PLC: Towards Efficient Packet Loss Concealment with Flow Matching
장준혁
IEEE SIGNAL PROCESSING LETTERS, 202503

9

Diff-PLC: A diffusion-based approach for effective packet loss concealment
장준혁
IEEE Spoken Language Technology Workshop (SLT), 202412

10

Proper Error Estimation and Calibration for Attention-Based Encoder-Decoder Models
장준혁
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 202411