From Dialect Gaps to Identity Maps: Tackling Variability in Speaker Verification

📅 2025-04-21
🏛️ arXiv.org
📈 Citations: 2
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the significant performance degradation of speaker verification in multidilectal Kurdish (Kurmanji, Sorani, Hawrami). We propose a dual-path framework integrating dialect-specific modeling and cross-dialect joint training. Methodologically, we construct the first annotated speech corpus covering all three major Kurdish dialects; design dialect-aware data augmentation, adversarial dialect-invariant feature learning, and multi-task loss optimization to robustly disentangle speaker identity representations from dialectal variation. Evaluated on cross-dialect test sets using an x-vector–based speaker embedding model, our approach achieves a 38.7% relative reduction in equal error rate (EER) compared to both single-dialect baselines and general multilingual speaker verification systems. This work constitutes the first systematic solution to cross-dialect speaker verification in Kurdish and establishes a novel paradigm for low-resource, multidilectal voice biometrics.

Technology Category

Application Category

📝 Abstract
The complexity and difficulties of Kurdish speaker detection among its several dialects are investigated in this work. Because of its great phonetic and lexical differences, Kurdish with several dialects including Kurmanji, Sorani, and Hawrami offers special challenges for speaker recognition systems. The main difficulties in building a strong speaker identification system capable of precisely identifying speakers across several dialects are investigated in this work. To raise the accuracy and dependability of these systems, it also suggests solutions like sophisticated machine learning approaches, data augmentation tactics, and the building of thorough dialect-specific corpus. The results show that customized strategies for every dialect together with cross-dialect training greatly enhance recognition performance.
Problem

Research questions and friction points this paper is trying to address.

Investigating Kurdish dialect variability challenges in speaker verification
Addressing phonetic and lexical differences across Kurmanji Sorani Hawrami dialects
Developing robust cross-dialect speaker identification through specialized training methods
Innovation

Methods, ideas, or system contributions that make the work stand out.

Advanced machine learning for dialect recognition
Data augmentation to enhance speaker verification
Cross-dialect training with dialect-specific corpora
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
A
A. A. Abdullah
Artificial Intelligence and Innovation Centre, University of Kurdistan Hewlér, Erbil, Kurdistan Region, Iraq
S
Soran Badawi
Language Center, Charmo University, Chamchamal, Kurdistan Region, Iraq
D
Dana A. Abdullah
Faculty of Engineering and Computer Science, Qaiwan International University, Sulaymaniyah, KRG, Iraq
D
D. R. Hamad
Computer Science Department, Faculty of Science, Soran University, Soran, Erbil, Kurdistan Region, Iraq
H
Hanan Abdulrahman Taher
S
S. Muhamad
A
A. Ahmed
B
B. Hassan
S
S. A. Aula
T
Tarik A. Rashid