I can tell whether you are a Native Hawl\^eri Speaker! How ANN, CNN, and RNN perform in NLI-Native Language Identification

2026-02-11

AI Summary

This study addresses the lack of native language identification (NLI) methods and speech resources for the Hawleri sub-dialect of Sorani Kurdish, a low-resource language variety. To bridge this gap, we present the first NLI speech dataset for Hawleri, comprising 24 hours of recordings from 40 speakers. We systematically evaluate the performance of artificial neural networks (ANNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs) on extremely short utterances as brief as one second. Through comprehensive experiments employing multiple time-window segmentation schemes, resampling techniques, and cross-validation strategies, our results demonstrate that RNNs achieve a classification accuracy of 95.92% on five-second audio segments, thereby confirming the effectiveness and feasibility of deep learning approaches for NLI in low-resource sub-dialect scenarios.

Technology Category

Natural Language Processing: SpeechMachine Learning: Large Multimodal Models (LMMs)Knowledge Representation and Reasoning: Knowledge Representation Languages

Application Category

Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web searchWeb Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web dataGraph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Native Language Identification (NLI) is a task in Natural Language Processing (NLP) that typically determines the native language of an author through their writing or a speaker through their speaking. It has various applications in different areas, such as forensic linguistics and general linguistics studies. Although considerable research has been conducted on NLI regarding two different languages, such as English and German, the literature indicates a significant gap regarding NLI for dialects and subdialects. The gap becomes wider in less-resourced languages such as Kurdish. This research focuses on NLI within the context of a subdialect of Sorani (Central) Kurdish. It aims to investigate the NLI for Hewl\^eri, a subdialect spoken in Hewl\^er (Erbil), the Capital of the Kurdistan Region of Iraq. We collected about 24 hours of speech by recording interviews with 40 native or non-native Hewl\^eri speakers, 17 female and 23 male. We created three Neural Network-based models: Artificial Neural Network (ANN), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN), which were evaluated through 66 experiments, covering various time-frames from 1 to 60 seconds, undersampling, oversampling, and cross-validation. The RNN model showed the highest accuracy of 95.92% for 5-second audio segmentation, using an 80:10:10 data splitting scheme. The created dataset is the first speech dataset for NLI on the Hewl\^eri subdialect in the Sorani Kurdish dialect, which can be of benefit to various research areas.

Problem

• Native Language Identification
• dialect
• subdialect
• low-resource language
• Sorani Kurdish

Innovation

• Native Language Identification
• Hewlêri dialect
• low-resource languages
• neural networks
• speech dataset