eess.ASNov 10, 2026

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

Authors: Zhuoyan Tao, Aditya Kommineni, Shrikanth Narayanan

Organizations: Signal and Image Processing Institute, Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California 90089, USA · Language Technologies Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA

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.

Figures & tables

Explore similar work

CardsList
  1. DiarizationLM: Speaker Diarization Post-Processing with Large Language Models

    Jan 7, 2024Quan Wang, Yiling Huang, Guanlong Zhao +3Speaker Diarization

  2. Efficiently Adapting Spoken Language Models for the Singaporean Context

    Jul 11, 2026Ng Jia Sheng JasonSpoken Language UnderstandingMulti-Task Learning

  3. LOPA: Enhancing Spoken Language Assessment via Latent Ordinal Prototype Alignment

    Jun 30, 2026Hong-Yun Lin, Fu-An Chao, Bi-Cheng Yan +1Prototype LearningOrdinal Regression