cs.SDOct 30, 2026

SPHERE: A Multi-Attribute No-Reference metric for Binaural Speech Quality And Spatial Fidelity

Authors: Bala Manikya Prasad Puram, Chandan K A Reddy, Artem Dementyev

Organizations: Google LLC

Abstract

In this paper, we introduce SPHERE (Spatial and Perceptual Human Evaluation and Rating Estimator), a multidimensional no-reference perceptual evaluation framework for binaural speech. SPHERE defines nine distinct perceptual and spatial attributes that characterize the immersive listening experience. We detail the crowdsourcing protocol and evaluation template used to collect ground-truth human ratings. To demonstrate the tractability of automating this framework, we evaluate six baseline configurations across single-branch and Siamese architectures utilizing Mel-spectrograms, complex STFTs, and pretrained spatial embeddings (PhaseCoder). Experimental results demonstrate that these baseline estimators achieve strong correlation with human subjective ratings, proving the feasibility of automated multidimensional spatial audio quality assessment.

Figures & tables

Explore similar work

Jun 4, 2026

Probing Spatial Structure in Pretrained Audio Representations

Pretrained spatial audio encoders are increasingly used as general-purpose representations for perceptual tasks, yet their spatial encoding capabilities remain poorly understood. We introduce the Spatial Audio Representation Learning (SARL) benchmark, a controlled framework for evaluating spatial information in pretrained audio models. SARL probes source-level factors (azimuth, elevation, distance, class) and room-level factors (RT60, volume, shape). Experiments across diverse encoders reveal three patterns: input configuration and training paradigm shape spatial encoding; source factors are consistently easier to decode than room factors; and sensitivity analysis under controlled perturbations shows heterogeneous responses to source and room variation. These results reveal systematic biases in current pretrained audio representations. SARL is released as an open-source benchmark for reproducible evaluation of spatial audio representations.
Jun 12, 2026

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

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.
Aug 10, 2026

Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions

Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Model (Audio-LLM) judges) are expected to reflect human perception, yet it is unclear how well they capture the distinct aspects of speech that listeners actually perceive. We deconstruct "naturalness" into a linguistically grounded annotation schema spanning 10 distinct perceptual dimensions, and use it to construct the first dimension-level meta-evaluation benchmark for TTS, comprising 860 utterances annotated by trained linguist raters. Results from benchmarking four MOS predictors and four Audio-LLM judges reveal that MOS predictors are more sensitive to acoustic signal-level properties at the prosodic and paralinguistic levels, while Audio-LLM judges show selective, prompt-dependent detection that favors word-level errors and does not generalize across all dimensions. Neither class reliably captures a breadth of linguistically structured, human-perceptible speech errors. Our dataset, annotation schema, and evaluation code are publicly released to support more targeted and interpretable TTS evaluation.