AUD-P8: Source Separation and Array Processing |
Session Type: Poster |
Time: Wednesday, 6 May, 16:30 - 18:30 |
Location: On-Demand |
Virtual Session: View on Virtual Platform |
Session Chair: Jonathan Le Roux, MERL |
AUD-P8.1: DEEP SPEECH EXTRACTION WITH TIME-VARYING SPATIAL FILTERING GUIDED BY DESIRED DIRECTION ATTRACTOR |
Yu Nakagome; Waseda University |
Masahito Togami; LINE Corporation |
Tetsuji Ogawa; Waseda University |
Tetsunori Kobayashi; Waseda University |
AUD-P8.2: ADAPTIVE BLIND AUDIO SOURCE EXTRACTION SUPERVISED BY DOMINANT SPEAKER IDENTIFICATION USING X-VECTORS |
Jakub Janský; Technical University of Liberec |
Jiří Málek; Technical University of Liberec |
Jaroslav Čmejla; Technical University of Liberec |
Tomáš Kounovský; Technical University of Liberec |
Zbyněk Koldovský; Technical University of Liberec |
Jindřich Žďánský; Technical University of Liberec |
AUD-P8.3: PASSIVE JOINT LOCALIZATION AND SYNCHRONIZATION OF DISTRIBUTED MICROPHONE ARRAYS |
Szymon Woźniak; AGH University of Science and Technology |
Konrad Kowalczyk; AGH University of Science and Technology |
AUD-P8.4: CONVERGENCE-GUARANTEED INDEPENDENT POSITIVE SEMIDEFINITE TENSOR ANALYSIS BASED ON STUDENT'S T DISTRIBUTION |
Tatsuki Kondo; University of Tokyo |
Kanta Fukushige; University of Tokyo |
Norihiro Takamune; University of Tokyo |
Daichi Kitamura; National Institute of Technology, Kagawa College |
Hiroshi Saruwatari; University of Tokyo |
Rintaro Ikeshita; NTT Corporation |
Tomohiro Nakatani; NTT Corporation |
AUD-P8.5: DETERMINED SOURCE SEPARATION USING THE SPARSITY OF IMPULSE RESPONSES |
Yuki Takahashi; Ritsumeikan University |
Daichi Kitahara; Ritsumeikan University |
Koichiro Matsuura; Ritsumeikan University |
Akira Hirabayashi; Ritsumeikan University |
AUD-P8.6: IMPROVING SPEAKER DISCRIMINATION OF TARGET SPEECH EXTRACTION WITH TIME-DOMAIN SPEAKERBEAM |
Marc Delcroix; NTT Corporation |
Tsubasa Ochiai; NTT Corporation |
Kateřina Žmolíková; Brno University of Technology |
Keisuke Kinoshita; NTT Corporation |
Naohiro Tawara; NTT Corporation |
Tomohiro Nakatani; NTT Corporation |
Shoko Araki; NTT Corporation |
AUD-P8.7: WHAMR!: NOISY AND REVERBERANT SINGLE-CHANNEL SPEECH SEPARATION |
Matthew Maciejewski; Johns Hopkins University |
Gordon Wichern; Mitsubishi Electric Research Laboratories (MERL) |
Emmett McQuinn; Whisper AI |
Jonathan Le Roux; Mitsubishi Electric Research Laboratories (MERL) |
AUD-P8.8: EIGENBEAM-ESPRIT FOR DOA-VECTOR ESTIMATION |
Adrian Herzog; Friedrich-Alexander Universität Erlangen |
Emanuël A. P. Habets; Friedrich-Alexander Universität Erlangen |
AUD-P8.12: BILEVEL OPTIMIZATION USING STATIONARY POINT OF LOWER-LEVEL OBJECTIVE FUNCTION |
Hiroaki Nakajima; University of Tokyo |
Daichi Kitamura; National Institute of Technology, Kagawa College |
Norihiro Takamune; University of Tokyo |
Hiroshi Saruwatari; University of Tokyo |
Nobutaka Ono; Tokyo Metropolitan University |