ASMSP-P7: Sound Source Detection, Extraction, and Separation
Thu, 3 Sep, 16:00 - 17:40
Location: Balcony I East
Session Type: Poster
Session Chair: Zbynek Koldovsky, Technical University of Liberec
Track: 1: ASMSP - Acoustic, Speech and Music Signal Processing
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P7.1: DECENTRALIZED INDEPENDENT LOW-RANK MATRIX ANALYSIS FOR BLIND SOURCE SEPARATION ON DISTRIBUTED MICROPHONE ARRAYS
Yuta Haruyama, Kouei Yamaoka, Norihiro Takamune, Hiroshi Saruwatari, The University of Tokyo, Japan
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P7.2: BINAURAL TARGET SPEAKER EXTRACTION USING INDIVIDUALIZED HRTF
Yoav Ellinson, Sharon Gannot, Bar-Ilan University, Israel
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P7.3: GENERALIZED TURN-TAKING–BASED CONVERSATIONAL PARTNER IDENTIFICATION IN MULTI-TALKER SCENARIOS USING VOICE ACTIVITY
Leila Eslami, Lars Dalskov Mosgaard, WS Audiology, Denmark; Jesper Rindom Jensen, Aalborg University, Denmark; Bolaji Adesokan, Eline Borch Petersen, WS Audiology, Denmark
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P7.4: Learning Input-Channel Permutation Equivariance for Multi-Channel Source Separation: Reducing Bleeding in Small Music Ensembles
Ruchi Pandey, Tampere University, Finland; Jaime Garcia-Martinez, Pablo Cabañas-Molero, University of Jaen, Spain, Spain; David Diaz-Guerra, Ricardo Falcón Pérez, Tuomas Virtanen, Tampere University, Finland; Julio J. Carabias-Orti, Pedro Vera-Candeas, University of Jaen, Spain, Spain
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P7.5: CINESUBNET: A MULTIMODAL ARCHITECTURE FOR TEXT-DRIVEN CINEMATIC AUDIO SOURCE SEPARATION
Marian Negru, Ana Nicolae, National University of Science and Technology POLITEHNICA Bucharest, Romania
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P7.6: REGION-CONDITIONED TARGET SPEAKER EXTRACTION VIA REVERBERATION CUES AND GAUSSIAN-KERNEL DISTANCE ENCODING
Shengjie Lu, Xiang Zhou, Yichen Yang, Bing Zhu, Wen Zhang, Northwestern Polytechnical University, China
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P7.7: Agnostic Blind Source Separation on Subsea Cables via Sum-of-Norms Bispectrum Tensor Factorization
Andersen Ang, University of Southampton, United Kingdom; Belal Mohammad, Hamid Shiri, National Oceanography Centre, United Kingdom; Timothy J Norman, University of Southampton, United Kingdom
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P7.8: Neural TTS-based Dynamic Data Augmentation for Improved Speech Separation
Kai Wang, Cuicui Zhu, Lili Yin, Xinjiang University, China; Sheng Li, Institute of Science Tokyo, Japan; Madina Mansurova, Al-Farabi Kazakh National University, Kazakhstan; Hao Huang, Xinjiang University, China