BINAQUAL: A Full-Reference Objective Localization Similarity Metric for Binaural Audio

2025-05-17

AI Summary

This study addresses the lack of reliable objective metrics for evaluating binaural audio spatial localization fidelity. We propose BINAQUAL—the first full-reference localization similarity metric specifically designed for the binaural domain. Methodologically, we pioneer the adaptation of Ambisonics-domain quality modeling to binaural audio, integrating key binaural cues—including interaural time difference (ITD), interaural level difference (ILD), and spectral distortion—within a framework that incorporates perceptually weighted frequency-band decomposition and spatial error normalization. This enables multidimensional sensitivity analysis across source azimuth, interpolation method, distortion type, and content diversity. Evaluated across five spatial degradation scenarios, BINAQUAL robustly discriminates fine-grained localization errors and achieves a Pearson correlation coefficient of 0.92 with MUSHRA subjective scores, demonstrating its effectiveness and novelty as a high-consistency, automated evaluation benchmark.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Security and Privacy: Large-scale security measurements

Abstract

Spatial audio enhances immersion in applications such as virtual reality, augmented reality, gaming, and cinema by creating a three-dimensional auditory experience. Ensuring the spatial fidelity of binaural audio is crucial, given that processes such as compression, encoding, or transmission can alter localization cues. While subjective listening tests like MUSHRA remain the gold standard for evaluating spatial localization quality, they are costly and time-consuming. This paper introduces BINAQUAL, a full-reference objective metric designed to assess localization similarity in binaural audio recordings. BINAQUAL adapts the AMBIQUAL metric, originally developed for localization quality assessment in ambisonics audio format to the binaural domain. We evaluate BINAQUAL across five key research questions, examining its sensitivity to variations in sound source locations, angle interpolations, surround speaker layouts, audio degradations, and content diversity. Results demonstrate that BINAQUAL effectively differentiates between subtle spatial variations and correlates strongly with subjective listening tests, making it a reliable metric for binaural localization quality assessment. The proposed metric provides a robust benchmark for ensuring spatial accuracy in binaural audio processing, paving the way for improved objective evaluations in immersive audio applications.

Problem

• Assessing localization similarity in binaural audio recordings
• Evaluating spatial fidelity affected by compression and encoding
• Providing objective metric for binaural audio quality assessment

Innovation

• Adapts AMBIQUAL metric for binaural audio
• Assesses localization similarity in recordings
• Correlates strongly with subjective tests