Tue PM1.L1: Audio Signal Separation and Restoration
Tue, 5 Sep, 14:30 - 16:10 Finland Time (UTC +3)
Location: EUROPAEA
Session Type: Lecture
Session Chair: Zbynek Koldovsky, Technical University of Liberec
Track: ASMSP - Acoustic, Speech and Music Signal Processing
Tue, 5 Sep, 14:30 - 14:50 Finland Time (UTC +3)

Tue PM1.L1.1: LOW-COMPLEXITY REAL-TIME NEURAL NETWORK FOR BLIND BANDWIDTH EXTENSION OF WIDEBAND SPEECH
Esteban Gómez, Aalto University and Voicemod S.L., Spain; Mohammad Hassan Vali, Tom Bäckström, Aalto University, Finland
Tue, 5 Sep, 14:50 - 15:10 Finland Time (UTC +3)

Tue PM1.L1.2: SPECTROGRAM INVERSION FOR AUDIO SOURCE SEPARATION VIA CONSISTENCY, MIXING, AND MAGNITUDE CONSTRAINTS
Paul Magron, Université de Lorraine, CNRS, Inria, LORIA, France; Tuomas Virtanen, Audio Research Group, Tampere University, Finland
Tue, 5 Sep, 15:10 - 15:30 Finland Time (UTC +3)

Tue PM1.L1.3: GEOMETRICALLY CONSTRAINED SOURCE EXTRACTION AND DEREVERBERATION BASED ON JOINT OPTIMIZATION
Yichen Yang, Xianrui Wang, Northwestern Polytechnical University, China; Andreas Brendel, Friedrich-Alexander-Universität, Germany; Wen Zhang, Northwestern Polytechnical University, China; Walter Kellermann, Friedrich-Alexander-Universität, Germany; Jingdong Chen, Northwestern Polytechnical University, China
Tue, 5 Sep, 15:30 - 15:50 Finland Time (UTC +3)

Tue PM1.L1.4: DISTRIBUTION PRESERVING SOURCE SEPARATION WITH TIME FREQUENCY PREDICTIVE MODELS
Pedro J. Villasana T., Janusz Klejsa, Lars Villemoes, Per Hedelin, Dolby Sweden AB, Sweden
Tue, 5 Sep, 15:50 - 16:10 Finland Time (UTC +3)

Tue PM1.L1.5: NEURAL FAST FULL-RANK SPATIAL COVARIANCE ANALYSIS FOR BLIND SOURCE SEPARATION
Yoshiaki Bando, National Institute of Advanced Industrial Science and Technology / RIKEN, Japan; Yoshiki Masuyama, Tokyo Metropolitan University / National Institute of Advanced Industrial Science and Technology, Japan; Aditya Arie Nugraha, RIKEN, Japan; Kazuyoshi Yoshii, RIKEN / Kyoto University, Japan