An Empirical Recipe for Universal Phone Recognition

View PDF HTML (experimental)

Abstract:Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive. Highly performant English-focused models do not generalize across languages, while multilingual models underutilize pretrained representations. It also remains unclear how data scale, architecture, and training objective contribute to multilingual PR. We present PhoneticXEUS -- trained on large-scale multilingual data and achieving state-of-the-art performance on both multilingual (17.7% PFER) and accented English speech (10.6% PFER). Through controlled ablations with evaluations across 100+ languages under a unified scheme, we empirically establish our training recipe and quantify the impact of SSL representations, data scale, and loss objectives. In addition, we analyze error patterns across language families, accented speech, and articulatory features. All data and code are released openly.

Comments: Submitted to Interspeech 2026. Code: this https URL

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2603.29042 [cs.CL]

(or arXiv:2603.29042v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2603.29042

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Shikhar Bharadwaj [view email] [v1] Mon, 30 Mar 2026 22:12:48 UTC (99 KB)