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
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 and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.
The Engineering Briefs at this Convention were selected on the basis of a submitted synopsis, ensuring that they are of interest to AES members, and are not overly commercial. These briefs have been reproduced from the authors' advance manuscripts, without editing, corrections, or consideration by the Review Board. The AES takes no responsibility for their contents. Paper copies are not available, but any member can freely access these briefs. Members are encouraged to provide comments that enhance their usefulness.