Abstract | ||
---|---|---|
Head-Related Transfer Function (HRTF) measurement and extraction are important tasks for personalized-spatial audio. Many laboratories have their own apparatuses for data-collection but few studies have compared their results to a common subject or have modeled inter-dataset variances. We present a Bayesian fusion method based on Gaussian process (GP) modeling of joint spatial-frequency HRTFs over different spherical-measurement grids. Neumann KU-100 dummy HRTFs from 7 labs in the "Club Fritz" study are compared and fused to each other based on learning a set of transformations from the GP data-likelihood and covariance assumptions; parameter and hyperparameter training is automatic. Experimental results show that fused models for horizontal and median-plane HRTFs generalize the datasets better than pre-transformed ones. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/WASPAA.2013.6701842 | 2013 IEEE WORKSHOP ON APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS (WASPAA) |
Keywords | Field | DocType |
Gaussian Process Regression, Data Fusion, Kronecker Product, Equalization, Windowing | Computer science,Electronic engineering,Gaussian process,Artificial intelligence,Audio signal processing,Covariance,Pattern recognition,Hyperparameter,Bayesian fusion,Sensor fusion,Transfer function,Analysis of covariance,Machine learning | Conference |
ISSN | Citations | PageRank |
1931-1168 | 4 | 0.53 |
References | Authors | |
2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuancheng Luo | 1 | 28 | 5.10 |
Dmitry N. Zotkin | 2 | 171 | 19.06 |
Ramani Duraiswami | 3 | 1721 | 161.98 |