Binaural based machine learning applications generally require a large number of HRTF (Head-Related Transfer Function) measurements. However, building an HRTF database from measurements of a large number of participants can be a time-consuming and tedious process. An alternative method is to combine the data from different existing databases to create a large training dataset. This is a significant challenge due to the large difference in measurement angles, filter size, normalization schemes, and sample rates inherent in different databases. Consequently, training of some machine learning algorithms can be cumbersome, requiring significant trial and error with different data and settings. To facilitate convenient preparation of datasets, this paper presents a Matlab-based tool that allows researchers to prepare and consolidate various HRTF datasets across different databases in a robust and fast manner. The tool is available online: https://github.com/Benjamin-Tsui/HRTF_preprocessing
(See document for exact affiliation information.)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
