Binaural Sound Event Localization and Detection based on HRTF Cues for Humanoid Robots

TL;DR

This paper presents a binaural sound event localization and detection system inspired by human spatial hearing, utilizing a new feature representation and a synthetic dataset to improve accuracy in realistic auditory scenes.

Contribution

It introduces the BiSELD task, a novel BTFF feature representation, and a CRNN-based model, along with a synthetic benchmark dataset for binaural sound localization and detection.

Findings

Achieved 87.1% F-score in sound event detection

Attained 4.4° average localization error

Demonstrated effectiveness of BTFF features in improving performance

Abstract

This paper introduces Binaural Sound Event Localization and Detection (BiSELD), a task that aims to jointly detect and localize multiple sound events using binaural audio, inspired by the spatial hearing mechanism of humans. To support this task, we present a synthetic benchmark dataset, called the Binaural Set, which simulates realistic auditory scenes using measured head-related transfer functions (HRTFs) and diverse sound events. To effectively address the BiSELD task, we propose a new input feature representation called the Binaural Time-Frequency Feature (BTFF), which encodes interaural time difference (ITD), interaural level difference (ILD), and high-frequency spectral cues (SC) from binaural signals. BTFF is composed of eight channels, including left and right mel-spectrograms, velocity-maps, SC-maps, and ITD-/ILD-maps, designed to cover different spatial cues across frequency bands and spatial axes. A CRNN-based model, BiSELDnet, is then developed to learn both spectro-temporal patterns and HRTF-based localization cues from BTFF. Experiments on the Binaural Set show that each BTFF sub-feature enhances task performance: V-map improves detection, ITD-/ILD-maps enable accurate horizontal localization, and SC-map captures vertical spatial cues. The final system achieves a SELD error of 0.110 with 87.1% F-score and 4.4{\deg} localization error, demonstrating the effectiveness of the proposed framework in mimicking human-like auditory perception.