SLP-P14.3
HIGH-FIDELITY SPEECH ENHANCEMENT VIA DISCRETE AUDIO TOKENS
Luca Lanzendörfer, Frédéric Berdoz, Antonis Asonitis, Roger Wattenhofer, ETH Zurich, Switzerland
Session:
SLP-P14: Generative and Representation-Based Models to Speech Enhancement Poster
Track:
Speech and Language Processing [SL]
Location:
Poster Area 28
Presentation Time:
Wed, 6 May, 09:00 - 11:00
Presentation
Discussion
Resources
No resources available.
Session SLP-P14
SLP-P14.1: PARAGSE: PARALLEL GENERATIVE SPEECH ENHANCEMENT WITH GROUP-VECTOR-QUANTIZATION-BASED NEURAL SPEECH CODEC
Fei Liu, Yang Ai, University of Science and Technology of China, China
SLP-P14.2: DISCONTSE: SINGLE-STEP DIFFUSION SPEECH ENHANCEMENT BASED ON JOINT DISCRETE AND CONTINUOUS EMBEDDINGS
Yihui Fu, Tim Fingscheidt, Technische Universität Braunschweig, Germany
SLP-P14.3: HIGH-FIDELITY SPEECH ENHANCEMENT VIA DISCRETE AUDIO TOKENS
Luca Lanzendörfer, Frédéric Berdoz, Antonis Asonitis, Roger Wattenhofer, ETH Zurich, Switzerland
SLP-P14.4: DISSR: DISENTANGLING SPEECH REPRESENTATION FOR DEGRADATION-PRIOR GUIDED CROSS-DOMAIN SPEECH RESTORATION
Ziqi Liang, Zhijun Jia, AntGroup, China; Chang Liu, USTC, China; Minghui Yang, Zhihong Lu, Jian Wang, AntGroup, China
SLP-P14.5: MODELING STRATEGIES FOR SPEECH ENHANCEMENT IN THE LATENT SPACE OF A NEURAL AUDIO CODEC
Sofiene Kammoun, CentraleSupélec, IETR (UMR CNRS 6164), France; Xavier Alameda-Pineda, Inria at Univ. Grenoble Alpes, CNRS, LJK, France; Simon Leglaive, CentraleSupélec, IETR (UMR CNRS 6164), France
SLP-P14.6: LAFUFU: LATENT ACOUSTIC FEATURES FOR ULTRA-FAST UTTERANCE RESTORATION
Radosław Łazarz, Samsung R&D Institute Poland, AGH University of Kraków, Poland; Mateusz Wosik, Mikołaj Pudo, Urszula Krywalska, Adam Cieślak, Samsung R&D Institute Poland, Poland
SLP-P14.7: Relative Time Intervals Representation for Word-level Timestamping with Masked Training
Quanwei Tang, Soochow University, China; Zhiyu Tang, University of Queenland, Australia; Xu Li, AISpeech Ltd, China; Dong Zhang, Shoushan Li, Guodong Zhou, Soochow University, China
SLP-P14.8: IS PHASE REALLY NEEDED FOR WEAKLY-SUPERVISED DEREVERBERATION ?
Marius Rodrigues, Louis Bahrman, Roland Badeau, Gaël Richard, Télécom Paris, France
SLP-P14.9: INFLUENCE OF CLEAN SPEECH CHARACTERISTICS ON SPEECH ENHANCEMENT PERFORMANCE
Mingchi Hou, Ina Kodrasi, Idiap Research Institute, Switzerland
SLP-P14.10: Ranking the Impact of Contextual Specialization in Neural Speech Enhancement
Peter Leer, Eriksholm Research Centre and Aalborg University, Denmark; Svend Feldt, Eriksholm Research Centre, Denmark; Zheng-Hua Tan, Jan Østergaard, Aalborg University, Denmark; Jesper Jensen, Eriksholm Research Centre and Aalborg University, Denmark
Contacts