AASP-P2: Audio Representation Learning
Poster
Tue, 5 May, 14:00 - 16:00
Location: Poster Area 26
Session Type: Poster
Track: Audio and Acoustic Signal Processing [AA]
Click the to view the manuscript on IEEE Xplore Open Preview

AASP-P2.1: GLAP: General contrastive audio-text pretraining across domains and languages
Heinrich Dinkel, Zhiyong Yan, Tianzi Wang, Yongqing Wang, Xingwei Sun, Yadong Niu, Jizhong Liu, Gang Li, Junbo Zhang, Jian Luan, Xiaomi, China

AASP-P2.2: SPATIAL-CLAP: LEARNING SPATIALLY-AWARE AUDIO–TEXT EMBEDDINGS FOR MULTI-SOURCE CONDITIONS
Kentaro Seki, Yuki Okamoto, Kouei Yamaoka, Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari, The University of Tokyo, Japan

AASP-P2.3: DSPAST: DISENTANGLED REPRESENTATIONS FOR SPATIAL AUDIO REASONING WITH LARGE LANGUAGE MODELS
Kevin Wilkinghoff, Zheng-Hua Tan, Aalborg University, Denmark

AASP-P2.4: SONAR: Self-Distilled Continual Pre-training for Domain Adaptive Audio Representation
Yizhou Zhang, Yuan Gao, Wangjin Zhou, Zicheng Yuan, Keisuke Imoto, Tatsuya Kawahara, Kyoto University, Japan

AASP-P2.5: ADAPTIVE PER-CHANNEL ENERGY NORMALIZATION FRONT-END FOR ROBUST AUDIO SIGNAL PROCESSING
Hanyu Meng, Vidhyasaharan Sethu, Eliathamby Ambikairajah, The University of New South Wales, Australia; Qiquan Zhang, Alibaba Group, China; Haizhou Li, The Chinese University of Hong Kong, China

AASP-P2.6: Lightweight and Generalizable Acoustic Scene Representations via Contrastive Fine-Tuning and Distillation
Kuang Yuan, Carnegie Mellon University, United States of America; Yang Gao, Xilin Li, Xinhao Mei, Syavosh Zadissa, Tarun Pruthi, Saeed Bagheri Sereshki, Meta Reality Labs, United States of America

AASP-P2.7: IMPROVING AUDIO EVENT RECOGNITION WITH CONSISTENCY REGULARIZATION
Shanmuka Sadhu, Rutgers University, United States of America; Weiran Wang, University of Iowa, United States of America

AASP-P2.8: ADAPTIVE EMBEDDING FUSION WITH CONTRASTIVE LEARNING FOR ROBUST FULLY FEW-SHOT CLASS-INCREMENTAL AUDIO CLASSIFICATION
Kai Guo, Xiang Xie, Shangkai Zhao, Beijing Institute of Technology, China

AASP-P2.9: INCREMENTAL LEARNING FOR AUDIO CLASSIFICATION WITH HEBBIAN DEEP NEURAL NETWORKS
Riccardo Casciotti, Tampere University, Finland; Alberto Antonietti, Francesco De Santis, Politecnico di Milano, Italy; Annamaria Mesaros, Tampere University, Finland

AASP-P2.10: A TASK-AWARE DUAL-LEVEL SELF-SUPERVISED LEARNING METHOD FOR EFFECTIVE SOUND EVENT DETECTION
Jun Liu, Qing Gu, Peng-fei Cai, Nan Jiang, Yan Song, University of Science and Technology of China, Hefei, China, China