DPLM: A Deep Perceptual Spatial-Audio Localization Metric

Abstract

Subjective evaluations are critical for assessing the perceptual realism of sounds in audio-synthesis driven technologies like augmented and virtual reality. However, they are challenging to set up, fatiguing for users, and expensive. In this work, we tackle the problem of capturing the perceptual characteristics of localizing sounds. Specifically, we propose a framework for building a general purpose quality metric to assess spatial localization differences between two binaural recordings. We model localization similarity by utilizing activation-level distances from deep networks trained for direction of arrival (DOA) estimation. Our proposed metric (DPLM) outperforms baseline metrics on correlation with subjective ratings on a diverse set of datasets, even without the benefit of any human-labeled training data.

References in corpus (5)

• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
• The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework
• Regression and Classification for Direction-of-Arrival Estimation with Convolutional Recurrent Neural Networks
• A Dataset of Reverberant Spatial Sound Scenes with Moving Sources for Sound Event Localization and Detection
• Objective Assessment of Spatial Audio Quality using Directional Loudness Maps