On The Relevance Of The Differences Between HRTF Measurement Setups For Machine Learning

TL;DR

This paper examines how differences in HRTF measurement setups impact machine learning applications in spatial audio, highlighting the importance of dataset compatibility and identifying key factors affecting model performance.

Contribution

It establishes common ground between various HRTF datasets, investigates the effects of dataset differences on machine learning, and identifies the most relevant factors influencing results.

Findings

Differences in measurement setups can significantly affect machine learning outcomes.

Combining datasets requires careful consideration of measurement conditions.

Certain measurement differences are more impactful than others.

Abstract

As spatial audio is enjoying a surge in popularity, data-driven machine learning techniques that have been proven successful in other domains are increasingly used to process head-related transfer function measurements. However, these techniques require much data, whereas the existing datasets are ranging from tens to the low hundreds of datapoints. It therefore becomes attractive to combine multiple of these datasets, although they are measured under different conditions. In this paper, we first establish the common ground between a number of datasets, then we investigate potential pitfalls of mixing datasets. We perform a simple experiment to test the relevance of the remaining differences between datasets when applying machine learning techniques. Finally, we pinpoint the most relevant differences.