Fang Kang

11 papers A* 1A 1Misc 1Journal 6Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Prediction?
CoRR
Yueyi Yang, Haotian Liu, Fang Kang, Mengqi Zhang, Zheng Lian, Hao Tang, Haoyu Chen
2026 A* conf
Temporal Calibrating and Distilling for Scene-Text Aware Text-Video Retrieval.
AAAI
Zhiqian Zhao, Liang Li, Lei Shen, Xichun Sheng, Yaoqi Sun, Fang Kang, Chenggang Yan
2026 J jnl
iMiGUE-Speech: A Spontaneous Speech Dataset for Affective Analysis.
CoRR
Sofoklis Kakouros, Fang Kang, Haoyu Chen
2025 — conf
Detection-Aware Inference for Robust Talking-Head Video Generation.
MMAsia Workshops
Seyyedhamid Azimidokht, Fang Kang, Yueyi Yang, Haoyu Chen
2025 A conf
Face2VoiceSync: Lightweight Face-Voice Consistency for Text-Driven Talking Face Generation.
INTERSPEECH
Fang Kang, Yin Cao, Haoyu Chen
2025 J jnl
Face2VoiceSync: Lightweight Face-Voice Consistency for Text-Driven Talking Face Generation.
CoRR
Fang Kang, Yin Cao, Haoyu Chen
2024 J jnl
PSELDNets: Pre-trained Neural Networks on Large-scale Synthetic Datasets for Sound Event Localization and Detection.
CoRR
Jinbo Hu, Yin Cao, Ming Wu, Fang Kang, Feiran Yang, Wenwu Wang, Mark D. Plumbley, Jun Yang
2024 J jnl
Performance analysis of unconstrained partitioned-block frequency-domain adaptive filters in under-modeling scenarios.
EURASIP J. Adv. Signal Process.
Zhengqiang Luo, Ziying Yu, Fang Kang, Feiran Yang, Jun Yang
2022 Misc conf
A Multi-Task Learning Method for Weakly Supervised Sound Event Detection.
ICASSP
Sichen Liu, Feiran Yang, Fang Kang, Jun Yang
2021 — conf
Real-Time Independent Vector Analysis with a Deep-Learning-Based Source Model.
SLT
Fang Kang, Feiran Yang, Jun Yang
2019 J jnl
A low-complexity permutation alignment method for frequency-domain blind source separation.
Speech Commun.
Fang Kang, Feiran Yang, Jun Yang