A Survey on Machine Learning Techniques for Head-Related Transfer Function Individualization

Machine learning (ML) has become pervasive in various research fields, including binaural synthesis personalization, which is crucial for sound in immersive virtual environments. Researchers have mainly addressed this topic by estimating the individual head-related transfer function (HRTF). HRTFs are utilized to render audio signals at specific spatial positions, thereby simulating real-world sound wave interactions with the human body. As such, an HRTF that is compliant with individual characteristics enhances the realism of the binaural simulation. This survey systematically examines the ML-based HRTF individualization works proposed in the literature. The analyzed works are organized according to the processing steps involved in the ML workflow, including the employed dataset, input and output types, data preprocessing operations, ML models, and model evaluation. In addition to categorizing the existing literature works, this survey discusses their achievements, identifies their limitations, and outlines aspects requiring further investigation at the crossroads of research communities in acoustics, audio signal processing, and machine learning.