ASMSP-L2.5
CLOSED-SET SPEAKER IDENTIFICATION USING FEW-SHOT TRANSDUCTIVE LEARNING
Gabriel Pîrlogeanu, Ana Neacșu, Horia Cucu, University Politehnica of Bucharest, Romania; Jean-Christophe Pesquet, Université Paris-Saclay, France; Ismail Ben Ayed, Ecole de Technologie Superieure (ETS) Montreal, Canada
Session:
ASMSP-L2: Speaker Representation and Verification Lecture
Track:
ASMSP - Acoustic, Speech and Music Signal Processing
Location:
Teatro del Sole
Presentation Time:
Tue, 9 Sep, 15:20 - 15:40 Italy Time (UTC +2)
Session Chair:
Justyna Krzywdziak, Samsung R&D Institute
Presentation
Discussion
Resources
No resources available.
Session ASMSP-L2
ASMSP-L2.1: HOW TO MERGE YOUR EMBEDDINGS: STATISTICAL VS ATTENTION-BASED SPEAKER EMBEDDING AGGREGATION FOR SPEAKER VERIFICATION WITH MULTIPLE ENROLLMENTS
Justyna Krzywdziak, Samsung R&D Institute, Poland; Piotr Masztalski, Samsung R&D Institute, AGH University of Krakow, Poland; Michal Romaniuk, Samsung R&D Institute, Poland; Milosz Dudek, Joanna Stepien, Samsung R&D Institute, AGH University of Krakow, Poland; Mateusz Matuszewski, Samsung R&D Institute, Poland; Daria Hemmerling, Samsung R&D Institute, AGH University of Krakow, Poland
ASMSP-L2.2: JOINT TRAINING OF SPEAKER EMBEDDING EXTRACTOR, SPEECH AND OVERLAP DETECTION FOR DIARIZATION
Petr Pálka, Federico Landini, Dominik Klement, Mireia Diez, Anna Silnova, Brno University of Technology, Czech Republic; Marc Delcroix, NTT Communication Science Laboratories, Japan; Lukáš Burget, Brno University of Technology, Czech Republic
ASMSP-L2.3: SPEAKER EMBEDDINGS TO IMPROVE TRACKING OF INTERMITTENT AND MOVING SPEAKERS
Taous Iatariene, Orange, Université de Lorraine, CNRS, Inria, Loria, France; Can Cui, Université de Lorraine, CNRS, Inria, Loria, France; Alexandre Guérin, Orange, France; Romain Serizel, Université de Lorraine, CNRS, Inria, Loria, France
ASMSP-L2.4: A FRAMEWORK FOR ROBUST SPEAKER VERIFICATION IN HIGHLY NOISY ENVIRONMENTS LEVERAGING BOTH NOISY AND ENHANCED AUDIO
Adam Katav, Yair Moshe, Israel Cohen, Technion - Israel Institute of Technology, Israel
ASMSP-L2.5: CLOSED-SET SPEAKER IDENTIFICATION USING FEW-SHOT TRANSDUCTIVE LEARNING
Gabriel Pîrlogeanu, Ana Neacșu, Horia Cucu, University Politehnica of Bucharest, Romania; Jean-Christophe Pesquet, Université Paris-Saclay, France; Ismail Ben Ayed, Ecole de Technologie Superieure (ETS) Montreal, Canada