Thu PM1.P: Acoustic signal modeling, representation and coding
Thu, 7 Sep, 14:00 - 15:40 Finland Time (UTC +3)
Location: Fennia Foyer
Session Type: Poster
Session Chair: Saikat Chatterjee, KTH Royal Institute of Technology
Track: ASMSP - Acoustic, Speech and Music Signal Processing

Thu PM1.P.1: Deep Joint Source-Channel Analog Coding for Low-Latency Speech Transmission over Gaussian Channels
Mohammad Bokaei, Jesper Jensen, Aalborg university, Denmark; Simon Doclo, University of Oldenburg, Germany; Jan Østergaard, Aalborg university, Denmark

Thu PM1.P.2: SIMULTANEOUS OR SEQUENTIAL TRAINING? HOW SPEECH REPRESENTATIONS COOPERATE IN A MULTI-TASK SELF-SUPERVISED LEARNING SYSTEM
Khazar Khorrami, María Andrea Cruz Blandón, Tuomas Virtanen, Okko Räsänen, Tampere University, Finland

Thu PM1.P.3: A Relaxed Optimization Approach for Adversarial Attacks against Neural Machine Translation Models
Sahar Sadrizadeh, Clément Barbier, EPFL, Switzerland; Ljiljana Dolamic, armasuisse S+T, Switzerland; Pascal Frossard, EPFL, Switzerland

Thu PM1.P.4: Optimization of Transmission Parameters in Fast Pulse-Echo Ultrasound Imaging using Sparse Recovery
Ozan Çakıroğlu, Fraunhofer-Institut für Zerstörungsfreie Prüfverfahren IZFP, Germany; Eduardo Pérez, Technische Universität Ilmenau, Germany; Florian Römer, Fraunhofer-Institut für Zerstörungsfreie Prüfverfahren IZFP, Germany; Martin Schiffner, Ruhr-University Bochum, Germany

Thu PM1.P.6: STACKED RES2NET-CBAM WITH GROUPED CHANNEL ATTENTION FOR MULTI-LABEL BIRD SPECIES CLASSIFICATION
Noumida A, Mukund R, Madhavan Nair N, College of Engineering Trivandrum, India; Rajeev Rajan, Govt. Engineering College, Barton Hill, Thiruvananthapuram, India

Thu PM1.P.7: LOW-COMPLEXITY AUDIO EMBEDDING EXTRACTORS
Florian Schmid, Khaled Koutini, Gerhard Widmer, Johannes Kepler University Linz, Austria