AASP-L1.3
BONE-CONDUCTION GUIDED MULTIMODAL SPEECH ENHANCEMENT WITH CONDITIONAL DIFFUSION MODELS
Sina Khanagha, Bunlong Lay, Timo Gerkmann, University of Hamburg, Germany
Session:
AASP-L1: Signal Enhancement, Restoration, and Extraction Oral
Track:
Audio and Acoustic Signal Processing [AA]
Location:
Room 127+128
Presentation Time:
Tue, 5 May, 14:40 - 15:00
Presentation
Discussion
Resources
No resources available.
Session AASP-L1
AASP-L1.1: ADAPTIVE ROTARY STEERING WITH JOINT AUTOREGRESSION FOR ROBUST EXTRACTION OF CLOSELY MOVING SPEAKERS IN DYNAMIC SCENARIOS
Jakob Kienegger, Timo Gerkmann, University of Hamburg, Germany
AASP-L1.2: FULL BAND DENOISING OF ROOM IMPULSE RESPONSE IN THE WAVELET DOMAIN WITH DICTIONARY LEARNING
Théophile Dupré, Romain Couderc, Miguel Moleron, Axel Coulon, Rémy Bruno, Arnaud Laborie, Trinnov Audio, France
AASP-L1.3: BONE-CONDUCTION GUIDED MULTIMODAL SPEECH ENHANCEMENT WITH CONDITIONAL DIFFUSION MODELS
Sina Khanagha, Bunlong Lay, Timo Gerkmann, University of Hamburg, Germany
AASP-L1.4: REAL-TIME STREAMING MEL VOCODING WITH GENERATIVE FLOW MATCHING
Simon Welker, Tal Peer, Timo Gerkmann, University of Hamburg, Germany
AASP-L1.5: VOTING-BASED PITCH ESTIMATION WITH TEMPORAL AND FREQUENTIAL ALIGNMENT AND CORRELATION AWARE SELECTION
Junya Koguchi, Tomoki Koriyama, CyberAgent, Inc., Japan
AASP-L1.6: SPIKE-DRIVEN LOW-POWER SPEECH BANDWIDTH EXTENSION
Donghyun Kim, Sangho Han, Joon-Hyuk Chang, Hanyang University, Korea, Republic of
Contacts