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 71번부터 80번까지의 결과를 표시합니다.

2024
Article

GENERALIZED SPECAUGMENT VIA MULTI-RECTANGLE INVERSE MASKING FOR ACOUSTIC SCENE CLASSIFICATION

  • 2024-04
  • ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
  • IEEE
Article

TEXT-ONLY UNSUPERVISED DOMAIN ADAPTATION FOR NEURAL TRANSDUCER-BASED ASR PERSONALIZATION USING SYNTHESIZED DATA

  • 2024-03
  • ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
  • IEEE
Article

Instance-level loss based multiple-instance learning framework for acoustic scene classification

  • 2024-01
  • Applied Acoustics
  • ELSEVIER SCI LTD
2023
Article

Towards Robust Packet Loss Concealment System With ASR-Guided Representations

  • 2023-12
  • 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
  • Institute of Electrical and Electronics Engineers Inc.
Article

Partitioning Attention Weight: Mitigating Adverse Effect of Incorrect Pseudo-labels for Self-Supervised ASR

  • 2023-12
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Article

Cross-Modal Learning for CTC-Based ASR: Leveraging CTC-Bertscore and Sequence-Level Training

  • 2023-12
  • 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
  • Institute of Electrical and Electronics Engineers Inc.
Article

Extending Self-Distilled Self-Supervised Learning For Semi-Supervised Speaker Verification

  • 2023-12
  • 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
  • Institute of Electrical and Electronics Engineers Inc.
Article

Robust Time-of-Arrival-Based Splitting Mean Moving Object Localization

  • 2023-12
  • IEEE Signal Processing Letters
  • IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Article

Knowledge Distillation From Offline to Streaming Transducer: Towards Accurate and Fast Streaming Model by Matching Alignments

  • 2023-12
  • 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
  • Institute of Electrical and Electronics Engineers Inc.
Article

AWMC: Online Test-Time Adaptation Without Mode Collapse for Continual Adaptation

  • 2023-12
  • 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
  • Institute of Electrical and Electronics Engineers Inc.