English

CLAP-Based Automatic Word Naming Recognition in Post-Stroke Aphasia

Audio and Speech Processing 2026-02-17 v1 Sound

Abstract

Conventional automatic word-naming recognition systems struggle to recognize words from post-stroke patients with aphasia because of disfluencies and mispronunciations, limiting reliable automated assessment in this population. In this paper, we propose a Contrastive Language-Audio Pretraining (CLAP) based approach for automatic word-naming recognition to address this challenge by leveraging text-audio alignment. Our approach treats word-naming recognition as an audio-text matching problem, projecting speech signals and textual prompts into a shared embedding space to identify intended words even in challenging recordings. Evaluated on two speech datasets of French post-stroke patients with aphasia, our approach achieves up to 90% accuracy, outperforming existing classification-based and automatic speech recognition-based baselines.

Keywords

Cite

@article{arxiv.2602.14584,
  title  = {CLAP-Based Automatic Word Naming Recognition in Post-Stroke Aphasia},
  author = {Yacouba Kaloga and Marina Laganaro and Ina Kodrasi},
  journal= {arXiv preprint arXiv:2602.14584},
  year   = {2026}
}

Comments

Submitted to EUSIPCO 2026

R2 v1 2026-07-01T10:38:12.912Z