MLSP-21.6
STUDY OF POSITIONAL ENCODING APPROACHES FOR AUDIO SPECTROGRAM TRANSFORMERS
Leonardo Pepino, Pablo Riera, Luciana Ferrer, University of Buenos Aires, Argentina
Session:
Deep Learning for Speech and Audio Processing II
Track:
Machine Learning for Signal Processing
Location:
Gather Area F
Presentation Time:
Tue, 10 May, 20:00 - 20:45 China Time (UTC +8)
Tue, 10 May, 12:00 - 12:45 UTC
Tue, 10 May, 12:00 - 12:45 UTC
Session Chair:
Paola Garcia, Johns Hopkins University
Session MLSP-21
MLSP-21.1: SELF-CRITICAL SEQUENCE TRAINING FOR AUTOMATIC SPEECH RECOGNITION
Chen Chen, Yuchen Hu, Nana Hou, Heqing Zou, Eng Siong Chng, Nanyang Technological University, Singapore; Xiaofeng Qi, Hachibot, China
MLSP-21.2: FastAudio: A Learnable Audio Front-End for Spoof Speech Detection
Quchen Fu, Zhongwei Teng, Jules White, Douglas Schmidt, Vanderbilt University, United States of America; Maria Powell, Vanderbilt University Medical Center, United States of America
MLSP-21.3: COMPLEX IRM-AWARE TRAINING FOR VOICE ACTIVITY DETECTION USING ATTENTION MODEL
Yifei Zhao, Yazid Attabi, Benoit Champagne, McGill University, Canada; Wei-Ping Zhu, Concordia University, Canada
MLSP-21.4: LEARNING CONTINUOUS REPRESENTATION OF AUDIO FOR ARBITRARY SCALE SUPER RESOLUTION
Jaechang Kim, Yunjoo Lee, Jungseul Ok, Pohang University of Science and Technology, Korea, Republic of; Seunghoon Hong, Korea Advanced Institute of Science and Technology, Korea, Republic of
MLSP-21.5: AN INVESTIGATION OF THE EFFECTIVENESS OF PHASE FOR AUDIO CLASSIFICATION
Shunsuke Hidaka, Kohei Wakamiya, Tokihiko Kaburagi, Kyushu University, Japan
MLSP-21.6: STUDY OF POSITIONAL ENCODING APPROACHES FOR AUDIO SPECTROGRAM TRANSFORMERS
Leonardo Pepino, Pablo Riera, Luciana Ferrer, University of Buenos Aires, Argentina