SLP-L3: Speech Enhancement Using Generative Models
Oral
Tue, 5 May, 16:30 - 18:30
Location: Room 114
Session Type: Oral
Track: Speech and Language Processing [SL]
Click the to view the manuscript on IEEE Xplore Open Preview
Tue, 5 May, 16:30 - 16:50

SLP-L3.1: MEANFLOWSE: ONE-STEP GENERATIVE SPEECH ENHANCEMENT VIA CONDITIONAL MEAN FLOW
Duojia Li, Shenghui Lu, Hongchen Pan, Zongyi Zhan, Qingyang Hong, Lin Li, Xiamen University, China
Tue, 5 May, 16:50 - 17:10

SLP-L3.2: HyFlowSE: Hybrid End-to-End Flow-Matching Speech Enhancement via Generative-Discriminative Learning
Yang Zhang, Wenbin Jiang, Zhen Wang, KaiYing Wu, Wen Zhang, Hangzhou Dianzi University, China; Fei Wen, Shanghai Jiao Tong University, China
Tue, 5 May, 17:10 - 17:30

SLP-L3.3: FLOWSE-GRPO: TRAINING FLOW MATCHING SPEECH ENHANCEMENT VIA ONLINE REINFORCEMENT LEARNING
Haoxu Wang, Biao Tian, Yiheng Jiang, Zexu Pan, Shengkui Zhao, Bin Ma, Daren Chen, Xiangang Li, Alibaba Group, China
Tue, 5 May, 17:30 - 17:50

SLP-L3.4: HCGAN: HARMONIC-COUPLED GENERATIVE ADVERSARIAL NETWORK FOR SPEECH SUPER-RESOLUTION IN LOW-BANDWIDTH SCENARIOS
Xin Wang, Yuan Gao, Xiaotong Wang, Yibin Tang, Aimin Jiang, College of Information Science and Engineering, Hohai University, China, China; Ying Chen, School of Microelectronics and Control Engineering, Changzhou University, China, China
Tue, 5 May, 17:50 - 18:10

SLP-L3.5: ALIGNING GENERATIVE SPEECH ENHANCEMENT WITH PERCEPTUAL FEEDBACK
Haoyang Li, Nanyang Technological University, Singapore; Nana Hou, Individual, United States of America; Yuchen Hu, Nanyang Technological University, Singapore; Jixun Yao, Northwestern Polytechnical University, China; Sabato Marco Siniscalchi, University of Palermo; Norwegian University of Science and Technology; Georgia Institute of Technology, Italy; Xuyi Zhuang, Nanyang Technological University, China; Deheng Ye, Wei Yang, Tencent, Singapore; Eng Siong Chng, Nanyang Technological University, Singapore
Tue, 5 May, 18:10 - 18:30

SLP-L3.6: PG-SE: PREDICTIVE ACCELERATION AND CORRECTION FOR GENERATIVE SPEECH ENHANCEMENT
Yikai Huang, Zhiyong Wu, Tsinghua University, China; Shiyin Kang, SenseTime Inc., China; Zijian Lin, Jinjiang Liu, Xiang Li, Renjie Yu, Tsinghua University, China