AASP-P4.4
SELD-MoHA: A Fine-Tuning Method with the Mixture of Heterogeneous Adapters for Sound Event Localization and Detection
Yun Liang, Peng Zhang, Luoan Gu, Cankun Zhong, Yishen Lin, Yan Chen, South China Agricultural University, China
Session:
AASP-P4: Acoustic Sensor Array Processing and Sound Event Localization Poster
Track:
Audio and Acoustic Signal Processing [AA]
Location:
Poster Area 25
Presentation Time:
Tue, 5 May, 16:30 - 18:30
Presentation
Discussion
Resources
No resources available.
Session AASP-P4
AASP-P4.1: TriAD: Tri-head with Auxiliary Duplicating Permutation Invariant Training for Multi-Task Sound Event Localization and Detection
Bingnan Duan, Yinhuan Dong, Tughrul Arslan, John Thompson, University of Edinburgh, United Kingdom of Great Britain and Northern Ireland
AASP-P4.2: FUN-SSL: FULL-BAND LAYER FOLLOWED BY U-NET WITH NARROW-BAND LAYERS FOR MULTIPLE MOVING SOUND SOURCE LOCALIZATION
Yuseon Choi, Gwangju Institute of Science and Technology, Deeply Inc., Korea, Republic of; Hyeonseung Kim, Jewoo Jun, Jong Won Shin, Gwangju Institute of Science and Technology, Korea, Republic of
AASP-P4.3: Reconstruction of Spherical Sound Source Radiation Characteristics with Graph Signal Processing
Shota Okubo, Ryosuke Watanabe, Tomoaki Konno, Toshiharu Horiuchi, KDDI Research, Inc., Japan
AASP-P4.4: SELD-MoHA: A Fine-Tuning Method with the Mixture of Heterogeneous Adapters for Sound Event Localization and Detection
Yun Liang, Peng Zhang, Luoan Gu, Cankun Zhong, Yishen Lin, Yan Chen, South China Agricultural University, China
AASP-P4.5: AN ENVELOPE SEPARATION AIDED MULTI-TASK LEARNING MODEL FOR BLIND SOURCE COUNTING AND LOCALIZATION
Jiaqi Du, Donghang Wu, Xihong Wu, Tianshu Qu, Peking University, China
AASP-P4.6: Event classification by physics-informed inpainting for distributed multichannel acoustic sensor with partially degraded channels
Noriyuki Tonami, NEC corporation, Japan; Wataru Kohno, NEC Laboratories America, Inc., United States of America; Yoshiyuki Yajima, Sakiko Mishima, Yumi Arai, Reishi Kondo, Tomoyuki Hino, NEC corporation, United States of America
AASP-P4.7: Recurrent Neural Beamformer for Multichannel Speech Enhancement Under Adverse Noise Condition
Zhi-Wei Tan, Yuan Liu, Nanyang Technological University, Singapore; Andy W. H. Khong, Nanyang Technological University; Lee Kong Chian School of Medicine, Singapore; Anh H. T. Nguyen, NamiTech JSC, Viet Nam
AASP-P4.8: Neural Optimisation of Fixed Beamformers With Flexible Geometric Constraints
Longfei Felix Yan, Victoria University of Wellington, New Zealand; Weilong Huang, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany; Thushara D. Abhayapala, Australian National University, Australia; Jinwei Feng, Alibaba, United States of America; W. Bastiaan Kleijn, Victoria University of Wellington, New Zealand
AASP-P4.9: EXPLAINABLE DNN-BASED BEAMFORMER WITH POSTFILTER
Adi Cohen, Bar-Ilan University, Israel; Daniel Wong, Jung-Suk Lee, Meta Reality Labs, United States of America; Sharon Gannot, Bar-Ilan University, Israel
AASP-P4.10: PSELDNETS: PRE-TRAINED NEURAL NETWORKS ON A LARGE-SCALE SYNTHETIC DATASET FOR SOUND EVENT LOCALIZATION AND DETECTION
Jinbo Hu, Institute of Acoustics, Chinese Academy of Sciences, China; Yin Cao, Xi'an Jiaotong-Liverpool University, China; Ming Wu, Institute of Acoustics, Chinese Academy of Sciences, China; Fang Kang, University of Oulu, Finland; Feiran Yang, Institute of Acoustics, Chinese Academy of Sciences, China; Wenwu Wang, University of Surrey, United Kingdom of Great Britain and Northern Ireland; Mark Plumbley, King’s College London, United Kingdom of Great Britain and Northern Ireland; Jun Yang, Institute of Acoustics, Chinese Academy of Sciences, China
Contacts