# Spectro-Temporal Interference Confounds Phase Encoding in Spatial Audio Foundation Models

arXiv: https://arxiv.org/abs/2606.14820 · HTML: https://mlsanity.com/paper/2606.14820/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 12 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning](https://mlsanity.com/paper/2206.08312/) (2022)
- [BAT: Learning to Reason about Spatial Sounds with Large Language Models](https://mlsanity.com/paper/2402.01591/) (2024)
- [WavJEPA: Semantic learning unlocks robust audio foundation models for raw waveforms](https://mlsanity.com/paper/2509.23238/) (2025)
- [DSpAST: Disentangled Representations for Spatial Audio Reasoning with Large Language Models](https://mlsanity.com/paper/2509.13927/) (2025)
- [Binaural Sound Event Localization and Detection based on HRTF Cues for Humanoid Robots](https://mlsanity.com/paper/2507.20530/) (2025)
- [Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio](https://mlsanity.com/paper/2310.10922/) (2023)
- [BINAQUAL: A Full-Reference Objective Localization Similarity Metric for Binaural Audio](https://mlsanity.com/paper/2505.11915/) (2025)
- [AudioMotionBench: Evaluating Auditory Motion Perception in Audio LLMs](https://mlsanity.com/paper/2511.13273/) (2025)
- [A hemispheric two-channel code accounts for binaural unmasking in humans](https://mlsanity.com/paper/2111.04637/) (2021)

## Abstract (arXiv)

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.