CV-18 NER: Augmented Common Voice for Named Entity Recognition from Arabic Speech

TL;DR

This paper introduces CV-18 NER, the first dataset for Arabic speech NER, and demonstrates that end-to-end models outperform traditional pipelines on this task, with publicly available resources for future research.

Contribution

It creates and releases the first annotated Arabic speech NER dataset and benchmarks end-to-end models, highlighting the effectiveness of multilingual pretraining and transfer learning.

Findings

End-to-end models outperform pipeline systems on Arabic speech NER.

Arabic-specific self-supervised pretraining improves ASR performance.

Larger models may be less effective in low-resource Arabic speech NER.

Abstract

End-to-end speech Named Entity Recognition (NER) aims to directly extract entities from speech. Prior work has shown that end-to-end (E2E) approaches can outperform cascaded pipelines for English, French, and Chinese, but Arabic remains under-explored due to its morphological complexity, the absence of short vowels, and limited annotated resources. We introduce CV-18 NER, the first publicly available dataset for NER from Arabic speech, created by augmenting the Arabic Common Voice 18 corpus with manual NER annotations following the fine-grained Wojood schema (21 entity types). We benchmark both pipeline systems (ASR + text NER) and E2E models based on Whisper and AraBEST-RQ. E2E systems substantially outperform the best pipeline configuration on the test set, reaching 37.0% CoER (AraBEST-RQ 300M) and 38.0% CVER (Whisper-medium). Further analysis shows that Arabic-specific self-supervised pretraining yields strong ASR performance, while multilingual weak supervision transfers more effectively to joint speech-to-entity learning, and that larger models may be harder to adapt in this low-resource setting. Our dataset and models are publicly released, providing the first open benchmark for end-to-end named entity recognition from Arabic speech https://huggingface.co/datasets/Elyadata/CV18-NER.