장준혁 프로필 사진

장준혁

Chang, Joon-Hyuk

공과대학

융합전자공학부

Scopus

연구분야

  • 음성음향신호처리 및 머신러닝

자료 필터

자료유형

발행연도

2011 ~ 2026
2011 2026

키워드

언어

전체 405건 중 31번부터 40번까지의 결과를 표시합니다.

2025
Article

Bayesian Language Model Adaptation for Personalized Speech Recognition

  • Lee, Mun-Hak ; 
  • MO, Ji-Hwan ; 
  • Kang, Ji-Hun ; 
  • Son, Jin-Young ; 
  • Chang, Joon-Hyuk
  • 2025-04
  • IEEE Signal Processing Letters
  • IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Article

Adaptive splitting mean online expectation-maximization method-based moving object localization

  • 2025-04
  • Digital Signal Processing: A Review Journal
  • ACADEMIC PRESS INC ELSEVIER SCIENCE
Article

Diffusion-based Target Device Style Transfer for Robust Acoustic Scene Classification

  • 2025-03
  • ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
  • Institute of Electrical and Electronics Engineers Inc.
Article

Progressive Subband Modeling for Artifacts-free Speech Super-resolution

  • 2025-03
  • ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
  • Institute of Electrical and Electronics Engineers Inc.
Article

Flow-PLC: Towards Efficient Packet Loss Concealment with Flow Matching

  • 2025-03
  • IEEE Signal Processing Letters
  • IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Article

Multimodal Emotion Recognition with Target Speaker-Based Facial Embeddings

  • 2025-03
  • ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
  • Institute of Electrical and Electronics Engineers Inc.
Article

Trainable Adaptive Score Normalization for Automatic Speaker Verification

  • 2025-03
  • ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
  • Institute of Electrical and Electronics Engineers Inc.
Article

Few-shot Keyword-incremental Learning Using Compositional Information

  • 2025-03
  • ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
  • Institute of Electrical and Electronics Engineers Inc.
Article

Quad-Net: Melspectrogram Vocoder with Convolutional Layers Restricted by the Quadrature Mirror Filter for Perfect Reconstruction

  • 2025-03
  • ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
  • Institute of Electrical and Electronics Engineers Inc.
Article

Diff-PLC: A Diffusion-Based Approach For Effective Packet Loss Concealment

  • 2025-01
  • 2024 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP, SLT
  • IEEE