ASMSP-P8: Audio Analysis, Restoration, and Synthesis
Thu, 3 Sep, 16:00 - 17:40
Location: Balcony I West
Session Type: Poster
Session Chair: Maximo Cobos, Universitat de València
Track: 1: ASMSP - Acoustic, Speech and Music Signal Processing
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P8.1: AUDIOSET-TOOLS: A PYTHON FRAMEWORK FOR TAXONOMY-AWARE AUDIOSET CURATION AND REPRODUCIBLE AUDIO RESEARCH
Stefano Giacomelli, Marco Giordano, University of L'Aquila, Italy; Claudia Rinaldi, National Inter-University Consortium for Telecommunications (CNIT), Italy; Fabio Graziosi, Department of Information Engineering, Computer Science and Mathematics, Italy
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P8.2: AUDIOSKETCH: CONTROLLABLE IMAGE-TO-AUDIO GENERATION VIA SEMANTIC-TEMPORAL ENERGY MODULATION
Jihyun Lee, Yonsei University, Korea (South); Jiahao Li, Microsoft Research Asia, China; Woojin Chung, Yonsei University, Korea (South); Yan Lu, Microsoft Research Asia, China; Hong-Goo Kang, Yonsei University, Korea (South)
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P8.3: ON THE USE OF DIFFERENTIABLE VITERBI DECODING FOR LINEAR-CHAIN CRFS
Sebastian Strahl, Johannes Zeitler, Meinard Müller, International Audio Laboratories Erlangen, Germany
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P8.4: Contrastive Music–Video Matching for Audio-Based Background Video Composition
Jun Taniguchi, Waseda University, Japan; Kunihiro Abe, Rie Shigyo, DAIICHIKOSHO CO.,LTD., Japan; Tetsuji Ogawa, Waseda University, Japan
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P8.5: SyncStream: Unifying Audiovisual Representation Learning and Generative Modeling in the Latent Space
Jinhua Liang, Queen Mary University of London, United Kingdom; Sebastian Braun, Microsoft Research, United States
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P8.6: DIGITAL AUDIO VIA UNLIMITED SENSING: OVERFLOW OVERCOMES CLIPPING AND OVERFLOW
Ruiming Guo, Ayush Bhandari, Imperial College London, United Kingdom
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P8.7: Lightweight Replay Attack Detection via Interpretable Physical Descriptors
Saba Nasiri, EPFL, Switzerland; Alireza Amirshahi, Milos Cernak, Logitech Europe, Switzerland
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P8.8: UNFOLDING FOR AUDIO QUALITY IMPROVEMENT IN THE PRESENCE OF NOISE AND REVERBERATION
Marian Negru, Ana Nicolae, Corneliu Burileanu, National University of Science and Technology POLITEHNICA Bucharest, Romania; Jean-Christophe Pesquet, Université Paris-Saclay, Inria, France
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P8.9: AUTOMATIC CONTEXTUAL AUDIO DENOISING
Diep Luong, Tampere University x Nokia, Finland; Konstantinos Drossos, Mikko Heikkinen, Nokia, Finland; Tuomas Virtanen, Tampere University, Finland
Thu, 3 Sep, 16:00 - 17:40

ASMSP-P8.10: ON THE TRACES OF AUDIO DEEPFAKES: ANALYSIS OF AUDIO COMPONENTS FOR DETECTION
Karla Schäfer, Raphael Antonious Frick, Fraunhofer SIT | ATHENE, Germany