CSLRConformer: A Data-Centric Conformer Approach for Continuous Arabic Sign Language Recognition on the Isharah Datase

TL;DR

This paper introduces CSLRConformer, a novel data-centric approach combining feature engineering, preprocessing, and a Conformer-based model to improve continuous Arabic sign language recognition, achieving state-of-the-art results.

Contribution

It presents a new architecture and systematic data processing pipeline for signer-independent CSLR, adapting the Conformer model from speech recognition to sign language.

Findings

Achieved 5.60% WER on development set

Secured 3rd place in ICCV 2025 challenge

Validated the effectiveness of cross-domain model adaptation

Abstract

The field of Continuous Sign Language Recognition (CSLR) poses substantial technical challenges, including fluid inter-sign transitions, the absence of temporal boundaries, and co-articulation effects. This paper, developed for the MSLR 2025 Workshop Challenge at ICCV 2025, addresses the critical challenge of signer-independent recognition to advance the generalization capabilities of CSLR systems across diverse signers. A data-centric methodology is proposed, centered on systematic feature engineering, a robust preprocessing pipeline, and an optimized model architecture. Key contributions include a principled feature selection process guided by Exploratory Data Analysis (EDA) to isolate communicative keypoints, a rigorous preprocessing pipeline incorporating DBSCAN-based outlier filtering and spatial normalization, and the novel CSLRConformer architecture. This architecture adapts the hybrid CNN-Transformer design of the Conformer model, leveraging its capacity to model local temporal dependencies and global sequence context; a characteristic uniquely suited for the spatio-temporal dynamics of sign language. The proposed methodology achieved a competitive performance, with a Word Error Rate (WER) of 5.60% on the development set and 12.01% on the test set, a result that secured a 3rd place ranking on the official competition platform. This research validates the efficacy of cross-domain architectural adaptation, demonstrating that the Conformer model, originally conceived for speech recognition, can be successfully repurposed to establish a new state-of-the-art performance in keypoint-based CSLR.