Off-target posterior mass: A training-free diagnostic for fine-tuning spoken language diarization probes

arXiv:2611.13430 · eess.AS, cs.CL, cs.SD · Submitted 2026-11-10 · Read on arXiv

eess.AS, cs.CL, cs.SD

Submitted: 2026-11-10

Updated: 2026-11-10

Comments: 10 pages, 2 figures, 3 tables. Submitted to JASA Express Letters

Code: https://github.com/snakers4/silero-vad

License: http://creativecommons.org/licenses/by/4.0/

The gist: Spoken Language Diarization (SLD) models provide frame-level language information of a speech recording.

Terminology

Abstract

Spoken Language Diarization (SLD) models provide frame-level language information of a speech recording. SLD modeling pipeline includes feature extraction from pre-trained speech models followed by clustering. Fine-tuning pre-trained speech models has shown performance gains for SLD with its magnitude being dataset dependent. Off-target Posterior Mass (OTPM), computed based on posterior language identification probabilities is proposed as a diagnostic metric to forecast performance gains from SLD fine-tuning. OTPM obtains positive correlation with probe gains, 0.56 on unseen synthetic bilingual data and 0.23 on real-world corpora. These results indicate promising potential of OTPM as a diagnostic metric for SLD.

Sources

Related papers