2 papers
eess.AS2026
Location-based Training with Complementary Folded Linear Orderings for Multichannel Speech Separation
Kaixuan Yang, Stijn Kindt, Nilesh Madhu
Location-based training (LBT) effectively resolves the output permutation problem in multichannel speech separation by imposing deterministic spatial orderings. For planar micropho…
eess.AS2024
Enhanced Deep Speech Separation in Clustered Ad Hoc Distributed Microphone Environments
Jihyun Kim, Stijn Kindt, Nilesh Madhu +1
Ad-hoc distributed microphone environments, where microphone locations and numbers are unpredictable, present a challenge to traditional deep learning models, which typically requi…