SOURCE-LINKED INTELLIGENCE

CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation Models

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Speech Quality Assessment (SQA) is essential for modern speech technologies, and recent non-intrusive SQA predictors increasingly rely on Speech Foundation Models (SFMs). However, because SFMs expose representations from many layers, it remains unclear which depths are most informative for MOS prediction and how multi-layer information should be combined reliably across backbones and datasets. We benchmark ten SFMs on four MOS datasets under three regimes: full fine-tuning, last-layer probing with a frozen encoder, and naive cross-layer weighted aggregation. We find that the best layer is stro

Read original source ↗ Open in workspace

recordType

paper

region

Global