Deep learning-based Personal Sound Zones (PSZs) rely on simulated acoustic transfer functions (ATFs) for training, yet idealized point-source models exhibit large sim-to-real gaps. While physically informed components improve generalization, individual contributions remain unclear. This paper presents a controlled ablation study on a head-pose-conditioned binaural PSZ renderer using the Binaural Spatial Audio Neural Network (BSANN). We progressively enrich simulated ATFs with three components: (i) anechoically measured frequency responses of the particular loudspeakers(FR), (ii) analytic circular-piston directivity (DIR), and (iii) rigid-sphere head-related transfer functions (RS-HRTF). Four configurations are evaluated via in-situ measurements with two dummy heads. Performance metrics include inter-zone isolation (IZI), inter-program interference (IPI), and crosstalk cancellation (XTC) over 100-20000 Hz. Results show FR provides spectral calibration, yielding modest XTC improvements and reduced inter-listener IPI imbalance. DIR delivers the most consistent sound-zone separation gains (10.05 dB average IZI/IPI). RS-HRTF dominates binaural separation, boosting XTC by +2.38/+2.89 dB (average 4.51 to 7.91 dB), primarily above 2 kHz, while introducing mild listener-dependent IZI/IPI shifts. These findings guide prioritization of measurements and models when constructing training ATFs under limited budgets.
Figures & tables
ID
FR ( Aℓ )
DIR ( Dℓ )
RS-HRTF ( HHRTF )
C0
No
No
No
C1
Yes
No
No
C2
Yes
Yes
No
C3
Yes
Yes
Yes
Table 1: Cumulative ablation configurations. Each stage builds upon the previous one by enabling an additional physically informed component.
Figure 1: Geometric configuration of the experimental testbed. The playback system features a 24-element loudspeaker array mounted on a rigid baffle, comprising two rows: 8 woofers ( 100 – 2000 Hz) and 16 tweeters ( 2 – 20 kHz). Two HATS are positioned symmetrically at a distance of 1.0 m from the array with lateral offsets of ±0.5 m relative to the centerline, oriented perpendicular to the array midpoint.
Figure 2: Broadband performance summary for the four cumulative configurations. Top row: log-mean metric values over 100–20,000 Hz for Listener 1 and Listener 2 under C0–C3. Bottom row: incremental changes under the cumulative ablation protocol (FR: C1 − C0; DIR: C2 − C1; RS-HRTF: C3 − C2).
Figure 3: Frequency-dependent IZI, IPI, and XTC for the four cumulative training configurations, evaluated at a single static pose. Legends correspond to C0 (baseline point-source simulation), C1 (+FR), C2 (+FR+DIR), and C3 (+FR+DIR+RS-HRTF). Top row: Listener 1. Bottom row: Listener 2.
Recent spatial self supervised audio models achieve high performance on localization tasks, raising questions about their encoding of microsecond interaural phase fine structures. We propose a psychoacoustic benchmark based on the binaural masking level difference to evaluate this. Using an equalization cancellation baseline and a GCC PHAT positive control we evaluate nine frozen audio models spanning binaural SSL, monaural SSL, and neural audio codecs. Four monaural negative controls yield zero BMLD confirming binaural specificity. Two general purpose binaural SSL models exhibit minimal phase sensitivity while dedicated binaural spatial SSL models achieve BMLD comparable to the analytical baseline. Progressive physical ablations show that general purpose binaural SSL models rely on spectro temporal interference textures rather than cross channel phase computation. High detection rates in speech reflect a confounding reliance on broadband envelopes rather than genuine phase encoding.
Yuxuan Chen, Haoyuan Yu, Peize He
The Chinese University of Hong Kong, Shenzhen · Jilin University · Hunan University +1
Head-related transfer function (HRTF) spatial upsampling from sparse measurements is a fundamental challenge in personalized binaural audio. We formulate HRTF upsampling as an operator learning problem and introduce SPARO, a neural operator that maps sparse measurements at a set of spatial directions to the HRTF field, a continuous representation that can be queried at arbitrary positions. SPARO projects the measurements onto a learned set of spherical latent modes, processes the latent modes with Transformer blocks, and decodes the resulting representations at query directions. On SONICOM, using the LAP24 measurement configuration, SPARO attains the best log-spectral distortion (LSD) and interaural level difference (ILD) error at every sparsity level from 3 to 100 measurements (18% lower LSD and 43% lower ILD error than the strongest baseline at 100 measurements) while remaining competitive in interaural time difference (ITD) error. It reconstructs a dense HRTF 15 to 373 times faster than the leading neural-field method RANF. We further validate the approach on HUTUBS, demonstrating its effectiveness across HRTF datasets.
Meenakshi Krishnan, You Zhang, Ramani Duraiswami +1
University of Maryland, College Park · Dolby Laboratories, Inc.
Auditory models are central tools for studying spatial hearing, yet their validation typically relies on heuristic performance metrics rather than principled statistical methods. We present two contributions building on a Bayesian sound localisation model that jointly infers sound direction from noisy perceptual features and individual head-related transfer functions (HRTFs). First, we derive an explicit likelihood function and validate it through parameter recovery on simulated data and fitting to behavioural responses from 33 participants, demonstrating that the framework reliably identifies individual sensorimotor and spectral parameters. Second, we use this framework to compare four HRTF template interpolation methods, showing that full-sphere spatial coverage and high-frequency spectral fidelity are the primary determinants of template quality, while the specific interpolation algorithm is secondary. Together, these results show that standard model-based statistical methods can address both fundamental questions in spatial hearing and applied problems such as perceptual HRTF evaluation. An open-source Python implementation is released alongside this work.
Dyson School of Design Engineering, Imperial College London, London, United Kingdom · Audio Communication Group, Technische Universität Berlin, Germany · Department of Industrial Systems Technology and Management, University of Padova, Vicenza, Italy