ASMSP-P9: Audio Source Separation and Extraction
Thu, 11 Sep, 09:00 - 10:40 Italy Time (UTC +2)
Location: Poster Area C
Session Type: Poster
Session Co-Chairs: Peter Karsmakers, SoundTalks N.V. and Riccardo Giampiccolo,
Track: ASMSP - Acoustic, Speech and Music Signal Processing

ASMSP-P9.1: A Comparative Study on Positional Encoding for Time-frequency Domain Dual-path Transformer-based Source Separation Models
Kohei Saijo, Tetsuji Ogawa, Waseda University, Japan

ASMSP-P9.2: DISENTANGLING SPEECH REPRESENTATIONS WITH MUTUAL INFORMATION ESTIMATORS FOR EXPRESSIVE SYNTHESIS
Thomas Kassiotis, University of Crete, Greece; Yannis Pantazis, Foundation for Research and Technology, Greece

ASMSP-P9.3: A MULTICHANNEL EXTENSION OF LANGUAGE-QUERIED AUDIO SOURCE SEPARATION VIA INDEPENDENT VECTOR ANALYSIS
Yuki Nakamura, Taishi Nakashima, Nobutaka Ono, Tokyo Metropolitan University, Japan

ASMSP-P9.4: CONTEXTUAL SOUND EVENT CLASSIFIER MODELS: DISENTANGLE ACOUSTIC CONDITION IN EMBEDDING SPACE
Sreenivasa Upadhyaya, KU Leuven, Belgium; Wim Buyens, SoundTalks N.V., Belgium; Wim Desmet, KU Leuven, Belgium; Peter Karsmakers, SoundTalks N.V., Belgium

ASMSP-P9.5: MULTIPLICATIVE UPDATE REFORMULATION OF ONLINE INDEPENDENT VECTOR ANALYSIS FOR SOURCE-DEPENDENT FORGETTING FACTOR CONTROL
Kaito Masuko, Taishi Nakashima, Nobutaka Ono, Tokyo Metropolitan University, Japan

ASMSP-P9.6: Theoretical Formulation of Online Independent Vector Analysis Using Framewise Probabilistic Generative Model
Yuto Ishikawa, Norihiro Takamune, Kouei Yamaoka, Hiroshi Saruwatari, The University of Tokyo, Japan

ASMSP-P9.7: REAL-TIME SINGLE-CHANNEL SPEAKER-CONDITIONED TARGET SPEAKER EXTRACTION USING TCN-CONFORMER WITH EFFICIENT SELF-ATTENTION MECHANISMS
Ragini Sinha, Christian Rollwage, Fraunhofer Institute for Digital Media Technology IDMT, Oldenburg Branch for Hearing, Speech and Audio Technology HSA, Germany, Germany; Simon Doclo, Department of Medical Physics and Acoustics and Cluster of Excellence Hearing4all, Carl von Ossietzky Universität Oldenburg, Germany, Germany

ASMSP-P9.8: Single-Channel Target Speech Extraction Utilizing Distance and Room Clues
Runwu Shi, Zirui Lin, Benjamin Yen, Jiang Wang, Ragib Amin Nihal, Kazuhiro Nakadai, Institute of Science Tokyo, Japan

ASMSP-P9.9: U-Net Based Dereverberation using Fusion of Spectral Representation of TEO and Raw Audio
Devdeep Shetranjiwala, Hemant Patil, Dhirubhai Ambani Institute of Information and Communication Technology, India