Global HRTF Interpolation via Learned Affine Transformation of Hyper-conditioned Features

04/06/2022
by   Jin-woo Lee, et al.
0

Estimating Head-Related Transfer Functions (HRTFs) of arbitrary source points is essential in immersive binaural audio rendering. Computing each individual's HRTFs is challenging, as traditional approaches require expensive time and computational resources, while modern data-driven approaches are data-hungry. Especially for the data-driven approaches, existing HRTF datasets differ in spatial sampling distributions of source positions, posing a major problem when generalizing the method across multiple datasets. To alleviate this, we propose a deep learning method based on a novel conditioning architecture. The proposed method can predict an HRTF of any position by interpolating the HRTFs of known distributions. Experimental results show that the proposed architecture improves the model's generalizability across datasets with various coordinate systems. Additional demonstrations using coarsened HRTFs demonstrate that the model robustly reconstructs the target HRTFs from the coarsened data.

READ FULL TEXT
research
07/22/2022

Head-Related Transfer Function Interpolation from Spatially Sparse Measurements Using Autoencoder with Source Position Conditioning

We propose a method of head-related transfer function (HRTF) interpolati...
research
11/02/2022

Neural Fourier Shift for Binaural Speech Rendering

We present a neural network for rendering binaural speech from given mon...
research
04/12/2022

Text-Driven Separation of Arbitrary Sounds

We propose a method of separating a desired sound source from a single-c...
research
10/27/2022

HRTF Field: Unifying Measured HRTF Magnitude Representation with Neural Fields

Head-related transfer functions (HRTFs) are a set of functions describin...
research
04/23/2023

Towards Controllable Audio Texture Morphing

In this paper, we propose a data-driven approach to train a Generative A...
research
12/29/2020

Data-driven audio recognition: a supervised dictionary approach

Machine hearing is an emerging area. Motivated by the need of a principl...
research
10/07/2021

Towards Faster Continuous Multi-Channel HRTF Measurements Based on Learning System Models

Measuring personal head-related transfer functions (HRTFs) is essential ...

Please sign up or login with your details

Forgot password? Click here to reset