2014/04/28 by Hendrik Barfuss, Barfuss, Hendrik, Walter Kellermann +1
Computer Science · Engineering · #Blind Source Separation Techniques #FOS: Computer and information sciences #Sound (cs.SD) #Speech and Audio Processing #Vehicle Noise and Vibration Control #Vibration and Dynamic Analysis
paper · pdf · doi:10.48550/arxiv.1404.6881
openalex publication_date 2014/04/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, the concept of an adaptation algorithm is proposed, which can\nbe used to blindly adapt the microphone array geometry of a humanoid robot such\nthat the performance of the underlying signal separation algorithm is improved.\nAs a decisive feature, an online performance measure for blind source\nseparation is introduced which allows a robust and reliable estimation of the\ninstantaneous separation performance based on currently observable data.\nExperimental results from a simulated environment confirm the efficacy of the\nconcept.\n