Kurdish Speech | Natural Language Processing (NLP) & AI Research

MULTILINGUAL TEXT INTELLIGENCE

NLP Lab

Advanced natural language processing laboratory and editor tailored for Kurdish, Persian, and English text architectures

Multilingual Workspace

Kurdish, Persian & English NLP Lab

Cross-Lingual Text Processing Studio

The NLP Lab is an interactive laboratory platform designed for comprehensive text analysis and transformation across Kurdish (Sorani & Kurmanji), Persian, and English. It incorporates advanced pipeline features including tokenization, stemming, lemmatization, NER, chunking, and keyword extraction.

Tokenization

Stop Words Removal

Stemming

Lemmatization

POS Tagging

Word Frequency

NER Entities

Chunking

Keywords

Language Detection (KU / FA / EN)

Open NLP Lab

RESEARCH LABORATORY

Kurdish Speech Lab

Explore our state-of-the-art interactive lab platform designed for speech recognition, audio processing, and voice intelligence

Advanced Computational Infrastructure

The Kurdish Speech Laboratory integrates advanced machine learning models specifically trained on low-resource linguistic data. Researchers, linguists, and developers can interactively test automatic speech recognition (ASR), transformer-based text-to-speech (TTS), optical character recognition (OCR), and deep voice processing engines in real time.

Speech Recognition (ASR)

Neural Voice Synthesis (TTS)

optical character recognition (OCR)

Enter Speech Laboratory Telegram Bot

Speech Lab Video

RESEARCH TOPICS

Discussion & Technical Insights

Key artificial intelligence and NLP concepts researched by our engineering team

Natural Language Processing

Enabling computers to interpret text and speech. Covers Tokenization, Lemmatization, POS Tagging, NER, and Chunking.

Generative AI & LLMs

Clarifying the architectural differences and overlaps between Generative AI, Large Language Models, and Foundation Models.

Prompt Engineering

Techniques including Zero-Shot, Few-Shot, Chain-of-Thought (CoT), Tree of Thoughts (ToT), and Retrieval Augmented Generation (RAG).

PEFT & Fine-Tuning

Parameter-Efficient Fine-Tuning methods (Prompt-tuning, P-tuning) to improve pretrained LLM performance with minimal compute cost.

FAQS

Have Questions? Check Out the FAQ

Common questions regarding speech synthesis, recognition, and editing

What is Text to Speech (TTS)?

Realistic Kurdish Text to Speech. TTS stands for Text-to-Speech. It is a technology that converts written text into spoken words. TTS systems take input text and use synthetic voices to produce spoken audio. These systems are widely used in accessibility features, automated customer service, navigation systems, and audiobook generation.

What is Speech to Text (ASR)?

Automatic Speech Recognition for Central Kurdish. ASR converts spoken language into written text (STT). ASR systems analyze audio input and transcribe it into textual output, making it possible to convert spoken words into a digital format that can be processed, stored, or analyzed by computers.

What is AsoSpell?

Precise and Fast for Editing Kurdish Texts. Flags spelling errors and makes suggestions for correction, flags punctuation errors and fixes them at ones, detects various spellings of words, and suggests the unified standard form.

ARTICLES & PUBLICATIONS

Research Articles

Explore our academic papers and publications on Kurdish speech and language processing

Kurdish end-to-end speech synthesis using deep neural networks

End-to-End Kurdish Speech Synthesis Based on Transfer Learning

Breaking Walls: Pioneering Automatic Speech Recognition for Central Kurdish: End-to-End Transformer Paradigm

Toward Kurdish language processing: Experiments in collecting and processing the AsoSoft text corpus

Jira: a Kurdish Speech Recognition System Designing and Building Speech Corpus and Pronunciation Lexicon

Automatic Meter Classification of Kurdish Poems

Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach

End-to-End Transformer-based Automatic Speech Recognition for Northern Kurdish: A Pioneering Approach

Enhancing Low Resource Language Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach

ABOUT US

Kurdish Speech is a research and business group working on natural language processing technologies for Kurdish language. Kurdish is a member of the Indo-Iranian branch of Indo-European languages spoken by over 40 million people mainly in Iraq, Turkey, Iran, Syria, Armenia, and Azerbaijan. Despite its diversity of dialects, Kurdish belongs to low-resourced languages in computational linguistics. Kurdish Speech conducts continuous research to develop computational resources, models, and real-world NLP applications.

Knowledge Enterprise

Kurdish Speech is a knowledge-based enterprise founded and managed by experts in Artificial Intelligence, Computer Engineering, and Computational Linguistics.

Language Data & Resources

A part from developing applications for Kurdish language, Kurdish Speech is working to provide language data and resources for Computer Speech and Language Processing of Kurdish language. Our activities to that end include, but are not limited to, providing text corpus, speech corpus, WordNet, lexicon and parallel corpora.

Speech Recognition & Tagging

Kurdish language speech data and its related resources like tags are of most important language resources which are required for NLP research and applications such as automatic speech recognition, speaker recognition, etc. In this project, speech data for Kurdish language (Central Kurdish) was designed and collected so that it could be used in automatic speech recognition, speaker recognition, phonology researches, dialect analysis, etc. So far, approximately 30 hours of speech has been recorded and transcribed in order to produce this corpus.

OUR EXPERTS

Meet Our Team

Dedicated researchers and engineers driving artificial intelligence and Kurdish language processing

Dr. Hadi Veisi

Sharif University

• Ph.D in Computer Engineering, Sharif University of Technology, Tehran, Iran, 2011.

• Faculty member at Faculty of New Sciences and Technologies (FNST) of University of Tehran.

Research Interests:

Digital Signal Processing, Speech Processing, Pattern Recognition, Artificial Neural Network, Fuzzy Logic.

Mohammad MohammadAmini

Avignon Université

• Ph.D. Student in Computer Science, Avignon Université, Avignon, France.

• M.Sc. in IT, Tarbiat Modares University, Tehran, Iran, 2018.

Research Interests:

Soft Computing, Artificial Neural Networks, Evolutionary Computing, Natural Language Processing.

Dr. Hawre Hosseini

Ryerson University

• Ph.D. in Computer Science, Ryerson University, Toronto, Canada, 2022.

Research Interests:

Natural Language Processing, Question Answering Systems, Semantic Technologies, Data Mining.

Abdulhady Abas

University of Soran

• Master in Artificial Intelligence, University of Soran, Kurdistan.

Research Interests:

Artificial Intelligence, Natural Language Processing, Speech Recognition.

Morteza Naserzade

Sharif University

• Master in Computational Linguistics, Sharif University of Technology, 2018.

Research Interests:

Kurdish Grammar, Computational Linguistics, Natural Language Processing.

Farhad Rahimi

University of Arak

• Ph.D. Student in Computer Software Engineering, University of Arak, Iran.

Research Interests:

Deep learning, Speech Recognition, Data Science, Text to Speech.

Wirya Fathy

University of Tehran

• Ph.D. Student in Information Technology, University of Tehran, Tehran, Iran.

Research Interests:

Deep learning, Speech Recognition.

Sabat Salih

University of Soran

• Master in Artificial Intelligence, University of Soran, Kurdistan.

Research Interests:

Artificial Intelligence, Natural Language Processing, Text to Speech.

Kozhin Awlla

University of Soran

• Master's student in Artificial Intelligence, University of Soran, Kurdistan.

Research Interests:

Artificial Intelligence, Natural Language Processing, Sentiment Analysis.

Kodo Yousif

Koya University

• B.Sc. Software Engineering, Koya University, Kurdistan.

Research Interests:

Web Development, Natural Language Processing.

Pioneering Speech AI & NLP for Kurdish Language

NLP Lab

Kurdish, Persian & English NLP Lab

Cross-Lingual Text Processing Studio

Kurdish Speech Lab

Advanced Computational Infrastructure

Spell Checker Lab

Spell Checker Lab

AsoSpell Standardizer & Corrector

Discussion & Technical Insights

Natural Language Processing

Generative AI & LLMs

Prompt Engineering

PEFT & Fine-Tuning

Have Questions? Check Out the FAQ

What is Text to Speech (TTS)?

What is Speech to Text (ASR)?

What is AsoSpell?

Research Articles

Kurdish end-to-end speech synthesis using deep neural networks

End-to-End Kurdish Speech Synthesis Based on Transfer Learning

Breaking Walls: Pioneering Automatic Speech Recognition for Central Kurdish: End-to-End Transformer Paradigm

Toward Kurdish language processing: Experiments in collecting and processing the AsoSoft text corpus

Jira: a Kurdish Speech Recognition System Designing and Building Speech Corpus and Pronunciation Lexicon

Automatic Meter Classification of Kurdish Poems

Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach

End-to-End Transformer-based Automatic Speech Recognition for Northern Kurdish: A Pioneering Approach

Enhancing Low Resource Language Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach

Knowledge Enterprise

Language Data & Resources

Speech Recognition & Tagging

Meet Our Team

Dr. Hadi Veisi

Mohammad MohammadAmini

Dr. Hawre Hosseini

Abdulhady Abas

Morteza Naserzade

Farhad Rahimi

Wirya Fathy

Sabat Salih

Kozhin Awlla

Kodo Yousif

Contact Information

Our Location

Direct Channels

Social & Repositories