[b]=[d]-[t]+[p]: Self-supervised Speech Models Discover Phonological Vector Arithmetic Paper • 2602.18899 • Published Mar 12 • 1
Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces Paper • 2603.12642 • Published Mar 13 • 1
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks Paper • 2411.05361 • Published Nov 8, 2024 • 5
POWSM: A Phonetic Open Whisper-Style Speech Foundation Model Paper • 2510.24992 • Published Oct 28, 2025 • 4