In this paper, to keep the inherent multi-dimensional structure, a tensor is firstly used to describe HRTFs. Then local spectral features in a low-dimensional ...
Head-related transfer functions (HRTFs) depend on frequencies, sound directions, and individuals with high dimensionality and complicated structure.
Local spectral feature extraction and compaction for HRTFs by nonnegative tensor factorization. Citing conference paper. Jul 2013. [object Object]. Qinghua ...
Jun 7, 2013 · 2: LOCAL SPECTRAL FEATURE EXTRACTION AND COMPACTION FOR HRTFS BY NONNEGATIVE TENSOR FACTORIZATION. Qinghua Huang; Shanghai University. Lin Li ...
Local spectral feature extraction and compaction for HRTFs by nonnegative tensor factorization ... extracted from HRTFs tensor by nonnegative tensor factorization ...
The proposed factorization decomposes an information-bearing matrix into complex factor matrices that represent the spectral dictionary and temporal codes.
The literature review shows that the differences in con- structing the PCA input matrix relate to the domain used. (time or frequency), the representation ( ...
AUDIO SPOTFORMING USING NONNEGATIVE TENSOR FACTORIZATION WITH ATTRACTOR-BASED REGULARIZATION ... Normal With Occasional Anomalies: Feature Extraction for ...
Jun 16, 2008 · This special issue focuses on the most recent advances in NMF/NTF methods, with emphasis on the efforts made particularly by the researchers ...
Missing: HRTFs | Show results with:HRTFs
Feb 23, 2022 · This review presents a high-level overview of the uses of machine learning (ML) to address several challenges in spatial auditory display ...