ASMSP-L1.2
ON THE DESIGN OF DIFFUSION-BASED NEURAL SPEECH CODECS
Pietro Foti, Andreas Brendel, Fraunhofer-Institut für Integrierte Schaltungen, Germany
Session:
ASMSP-L1: Neural Audio Codecs and Compression Lecture
Track:
ASMSP - Acoustic, Speech and Music Signal Processing
Location:
Sala Massimo
Presentation Time:
Tue, 9 Sep, 11:10 - 11:30 Italy Time (UTC +2)
Session Co-Chairs:
Gaël Richard, Télécom Paris and Nikolay Gaubitch,
Presentation
Discussion
Resources
No resources available.
Session ASMSP-L1
ASMSP-L1.1: QINCODEC: NEURAL AUDIO COMPRESSION WITH IMPLICIT NEURAL CODEBOOKS
Zineb Lahrichi, Télécom Paris/Sony, France; Gaëtan Hadjeres, Sony, France; Gaël Richard, Geoffroy Peeters, Télécom Paris, France
ASMSP-L1.2: ON THE DESIGN OF DIFFUSION-BASED NEURAL SPEECH CODECS
Pietro Foti, Andreas Brendel, Fraunhofer-Institut für Integrierte Schaltungen, Germany
ASMSP-L1.3: SOFT DISENTANGLEMENT IN FREQUENCY BANDS FOR NEURAL AUDIO CODECS
Benoît Giniès, Xiaoyu Bie, Olivier Fercoq, Gaël Richard, Télécom Paris, Institut Polytechnique de Paris, France
ASMSP-L1.4: Spherical Lattice Vector Quantization in Neural Audio Coding
Thomas Muller, Stéphane Ragot, Orange Research, France; Pascal Scalart, IRISA, University of Rennes, France
ASMSP-L1.5: EXPLOITING NEURAL AUDIO CODECS FOR EDGE-TO-GATEWAY SPEECH PROCESSING
Stefano Ciapponi, Elisabetta Farella, Fondazione Bruno Kessler, Italy