OD-SLA-7.1

CNN-BASED DISCRIMINATIVE TRAINING FOR DOMAIN COMPENSATION IN ACOUSTIC EVENT DETECTION WITH FRAME-WISE CLASSIFIER

Tiantian Tang, Xinyuan Zhou, Yanhua Long, Shanghai Normal University, China; Yijie Li, Jiaen Liang, Unisound AI Technology Co., Ltd., China
Session:
Acoustics and Sound Event Processing
Track:
Speech, Language, and Audio (SLA)
Session Time:
Fri, 17 Dec, 13:00 - 15:00 Japan Standard Time (UTC +9)
Fri, 17 Dec, 04:00 - 06:00 Coordinated Universal Time
Thu, 16 Dec, 23:00 - 01:00 Eastern Standard Time (UTC -5)
Thu, 16 Dec, 20:00 - 22:00 Pacific Standard Time (UTC -8)
Session Chair:
Christian Ritz, University of Wollongong
Presentation
Not logged in.
Discussion
Not logged in.
Resources
Not logged in.
Session OD-SLA-7
FR2.OD-A.1: CNN-BASED DISCRIMINATIVE TRAINING FOR DOMAIN COMPENSATION IN ACOUSTIC EVENT DETECTION WITH FRAME-WISE CLASSIFIER
Tiantian Tang, Xinyuan Zhou, Yanhua Long, Shanghai Normal University, China; Yijie Li, Jiaen Liang, Unisound AI Technology Co., Ltd., China
FR2.OD-A.2: Frequency Axis Pooling Method for Weakly Labeled Sound Event Detection and Classification
Miao Liu, Jing Wang, Beijing Institute of Technology, China; Yujun Wang, Xiaomi Inc., China; Lidong Yang, Inner Mongolia University of Science and Technology, China
FR2.OD-A.3: A multi-source localization method based on clustering and outlier removal
Shang Gao, Maoshen Jia, Changchun Bao, Beijing University of Technology, China
FR2.OD-A.4: IMPULSIVE TIMING DETECTION BASED ON MULTI-FRAME PHASE VOTING FOR ACOUSTIC EVENT DETECTION
Sakiko Mishima, Reishi Kondo, NEC Corporation, Japan
FR2.OD-A.5: MULTIPLE-EMBEDDING SEPARATION NETWORKS: SOUND CLASS-SPECIFIC FEATURE EXTRACTION FOR UNIVERSAL SOUND SEPARATION
Hokuto Munakata, Ryu Takeda, Kazunori Komatani, Osaka University, Japan
FR2.OD-A.6: NARROW-EDGED BEAMFORMING USING MASKED PARAMETRIC ARRAY LOUDSPEAKERS
Yuting GENG, Haonan WANG, Takanobu NISHIURA, Ritsumeikan University, Japan; Masato NAKAYAMA, Osaka Sangyo University, Japan
FR2.OD-A.7: COPRIME MICROPHONE ARRAYS FOR ESTIMATING SPEECH DIRECTION OF ARRIVAL USING DEEP LEARNING
Jiahong Zhao, Christian Ritz, University of Wollongong, Australia
FR2.OD-A.8: A STRONGLY-LABELLED POLYPHONIC DATASET OF URBAN SOUNDS WITH SPATIOTEMPORAL CONTEXT
Kenneth Ooi, Karn Watcharasupat, Santi Peksi, Furi Andi Karnapi, Zhen-Ting Ong, Danny Chua, Hui-Wen Leow, Li-Long Kwok, Xin-Lei Ng, Zhen-Ann Loh, Woon-Seng Gan, Nanyang Technological University, Singapore
FR2.OD-A.9: FORMULATION OF Multidimensional FREQUENCY CHARACTERISTICS OF SECOND-ORDER NONLINEAR IIR FILTER
Kenta Iwai, Takanobu Nishiura, Ritsumeikan University, Japan; Yoshinobu Kajikawa, Kansai University, Japan
FR2.OD-A.10: TWO-STAGE PHASE RECONSTRUCTION USING DNN AND VON MISES DISTRIBUTION-BASED MAXIMUM LIKELIHOOD
Binh Thien Nguyen, Kenta Iwai, Takanobu Nishiura, Ritsumeikan University, Japan; Yukoh Wakabayashi, Tokyo Metropolitan University, Japan
FR2.OD-A.11: SHARP-SOUND-IMAGE CONSTRUCTION METHOD USING MULTICHANNEL SOUND SYSTEM WITH OPTIMAL PARAMETRIC LOUDSPEAKER ARRANGEMENT
Yuna Harada, Naoto Shimada, Haonan Wang, Kenta Iwai, Takanobu Nishiura, Ritsumeikan University, Japan; Masato Nakayama, Osaka Sangyo University, Japan
FR2.OD-A.12: VIRTUAL SOUND SOURCE RENDERING BASED ON DISTANCE CONTROL TO PENETRATE LISTENERS USING SURROUND PARAMETRIC-ARRAY AND ELECTRODYNAMIC LOUDSPEAKERS
Takuma Ekawa, Masato Nakayama, Toru Takahashi, Osaka Sangyo University, Japan
FR2.OD-A.13: SELF-ROTATION ANGLE ESTIMATION OF CIRCULAR MICROPHONE ARRAY BASED ON SOUND FIELD INTERPOLATION
Guansan Lian, Yukoh Wakabayashi, Taishi Nakashima, Nobutaka Ono, Tokyo Metropolitan University, Japan