Da-Hee Yang

19 papers A 3C 3Misc 1Journal 10Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
A dual-branch parallel network for speech enhancement and restoration.
Comput. Speech Lang.
Da-Hee Yang, Dail Kim, Joon-Hyuk Chang, Jeonghwan Choi, Han-Gil Moon
2026 J jnl
An experimental study of diffusion-based general speech restoration with predictive-guided conditioning.
Comput. Speech Lang.
Da-Hee Yang, Joon-Hyuk Chang
2026 J jnl
Latent-Level Enhancement With Flow Matching for Robust Automatic Speech Recognition.
IEEE Signal Process. Lett.
Da-Hee Yang, Joon-Hyuk Chang
2026 J jnl
Latent-Level Enhancement with Flow Matching for Robust Automatic Speech Recognition.
CoRR
Da-Hee Yang, Joon-Hyuk Chang
2025 C conf
A Momentum-Based Framework with Contrastive Data Generation for Robust Sound Source Localization.
ASRU
Hyun-Soo Kim, Da-Hee Yang, Joon-Hyuk Chang
2025 J jnl
FLOWER: Flow-Based Estimated Gaussian Guidance for General Speech Restoration.
CoRR
Da-Hee Yang, Jaeuk Lee, Joon-Hyuk Chang
2025 J jnl
Flow-PLC: Towards Efficient Packet Loss Concealment With Flow Matching.
IEEE Signal Process. Lett.
Da-Hee Yang, Joon-Hyuk Chang
2025 C conf
Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion.
ASRU
DongHoon Lim, Youngchae Kim, Dong-Hyun Kim, Da-Hee Yang, Joon-Hyuk Chang
2025 J jnl
Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion.
CoRR
DongHoon Lim, Youngchae Kim, Dong-Hyun Kim, Da-Hee Yang, Joon-Hyuk Chang
2025 A conf
Spatially Weighted Contrastive Learning for Robust Sound Source Localization.
INTERSPEECH
Hyun-Soo Kim, Da-Hee Yang, Joon-Hyuk Chang
2025 J jnl
Tokenized Generative Speech Enhancement With Language Model and Flow Matching.
IEEE Signal Process. Lett.
Da-Hee Yang, Jaeuk Lee, Joon-Hyuk Chang
2024 J jnl
DM: Dual-path Magnitude Network for General Speech Restoration.
CoRR
Da-Hee Yang, Dail Kim, Joon-Hyuk Chang, Jeonghwan Choi, Han-Gil Moon
2024 — conf
Diff-PLC: A Diffusion-Based Approach For Effective Packet Loss Concealment.
SLT
Da-Hee Yang, Joon-Hyuk Chang
2024 A conf
Guided conditioning with predictive network on score-based diffusion model for speech enhancement.
INTERSPEECH
Dail Kim, Da-Hee Yang, Donghyun Kim, Joon-Hyuk Chang, Jeonghwan Choi, Moa Lee, Jaemo Yang, Han-Gil Moon
2023 J jnl
Attention-based latent features for jointly trained end-to-end automatic speech recognition with modified speech enhancement.
J. King Saud Univ. Comput. Inf. Sci.
Da-Hee Yang, Joon-Hyuk Chang
2023 — conf
Masked Frequency Modeling for Improving Packet Loss Concealment in Speech Transmission Systems.
WASPAA
Da-Hee Yang, Donghyun Kim, Joon-Hyuk Chang
2023 Misc conf
Selective Film Conditioning with CTC-Based ASR Probability for Speech Enhancement.
ICASSP
Da-Hee Yang, Joon-Hyuk Chang
2023 C conf
Towards Robust Packet Loss Concealment System With ASR-Guided Representations.
ASRU
Da-Hee Yang, Joon-Hyuk Chang
2022 A conf
FiLM Conditioning with Enhanced Feature to the Transformer-based End-to-End Noisy Speech Recognition.
INTERSPEECH
Da-Hee Yang, Joon-Hyuk Chang