[2604.02102] Prosodic ABX: A Language-Agnostic Method for Measuring Prosodic Contrast in Speech Representations

Computer Science > Computation and Language arXiv:2604.02102 (cs) [Submitted on 2 Apr 2026] Title:Prosodic ABX: A Language-Agnostic Method for Measuring Prosodic Contrast in Speech Representations Authors:Haitong Sun, Stephen McIntosh, Kwanghee Choi, Eunjung Yeo, Daisuke Saito, Nobuaki Minematsu View a PDF of the paper titled Prosodic ABX: A Language-Agnostic Method for Measuring Prosodic Contrast in Speech Representations, by Haitong Sun and 5 other authors View PDF HTML (experimental) Abstract:Speech representations from self-supervised speech models (S3Ms) are known to be sensitive to phonemic contrasts, but their sensitivity to prosodic contrasts has not been directly measured. The ABX discrimination task has been used to measure phonemic contrast in S3M representations via minimal pairs. We introduce prosodic ABX, an extension of this framework to evaluate prosodic contrast with only a handful of examples and no explicit labels. Also, we build and release a dataset of English and Japanese minimal pairs and use it along with a Mandarin dataset to evaluate contrast in English stress, Japanese pitch accent, and Mandarin tone. Finally, we show that model and layer rankings are often preserved across several experimental conditions, making it practical for low-resource settings. Comments: Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG); Sound (cs.SD); Audio and Speech Processing (eess.AS) Cite as: arXiv:2604.02102 [cs.CL]   (or arXiv:2604.02102v1 [cs.C...