🧑‍🔬 Ajinkya Kulkarni

🏛️ Affiliations

🔬Idiap Research InstituteMartigny-Combe · Switzerland2015–2026 · 14 papersEmployment since 2024current🎓Mohamed bin Zayed University of Artificial IntelligenceAbu Dhabi · United Arab Emirates2022–2026 · 9 papersEmployment 2022–2024 · Postdoctoral Researcher, Natural Language Processingcurrent🎓Université de LorraineNancy · France2017–2022 · 7 papersEducation 2017–2018 · Master 2, Language Communication Technology, IDMC🔬Centre National de la Recherche ScientifiqueParis · France2020–2022 · 6 papers🔬Institut national de recherche en sciences et technologies du numériqueLe Chesnay-Rocquencourt · France2020–2022 · 5 papers🔬Laboratoire Lorrain de Recherche en Informatique et ses ApplicationsNancy · France2018–2022 · 5 papersEmployment 2018 · Research Intern, Multispeech🔬Centre Inria de l'Université de LorraineVillers-lès-Nancy · France2020–2023 · 4 papers🔬MULTISPEECH: La parole multimodale en interactionVillers-lès-Nancy · France2020–2023 · 4 papers🔬Centre for Development of Advanced ComputingPune · India2012–2016 · 1 paperEducation 2012 · Post Graduate Diploma, Embedded system Design, Computer ScienceEmployment 2013–2016 · Research Engineer, GIST Multilingual group

🏛️Validsoft Pvt LtdLondon · United Kingdom2022–2024Employment 2022–2024 · Research Consultant, Research and Development

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. ArTST: Arabic Text and Speech Transformer (2023 · 27 citations)
   Arabic lacked an open pre-trained model that handles both speech and text as input and output. English SpeechT5, when fine-tuned on Arabic, stayed strongly biased toward English and produced weak results. The authors built ArTST by keeping the SpeechT5 design: a shared T5-style encoder-decoder with separate small…
2. ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus (2023 · 27 citations)
   Arabic speech synthesis lags behind English largely because there is little suitable training data. Freely available Arabic speech collections tend to be multi-speaker and casual, with uneven recording quality. Corpora built specifically for TTS are compact sets designed for phonetic coverage, too small for modern…
3. Yet Another Model for Arabic Dialect Identification (2023 · 10 citations)
   The paper addresses spoken Arabic dialect identification (ADI). On the two standard benchmarks, ADI-5 (MGB-3) and ADI-17 (MGB-5), the winning challenge systems had never been beaten in later work. The authors limit their search to a 2×2 grid. The networks are ResNet and ECAPA-TDNN, both borrowed from speaker…

All works

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. ArTST: Arabic Text and Speech TransformerArabic Natural Language Processing Conference (ArabicNLP)Hawau Olamide Toyin, Amirbek Djanibekov, Ajinkya Kulkarni, et al.2023 · 27 citations
2. ClArTTS: An Open-Source Classical Arabic Text-to-Speech CorpusInterspeechAjinkya Kulkarni, Atharva Kulkarni, Sara Abedalmonem Mohammad Shatnawi, et al.2023 · 27 citations
3. Yet Another Model for Arabic Dialect IdentificationArabic Natural Language Processing Conference (ArabicNLP)Ajinkya Kulkarni, Hanan Aldarmaki2023 · 10 citations
4. GECko+: a Grammatical and Discourse Error Correction Tool ↗Actes de la 28e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 3 : Démonstrations · no summary yetEduardo Calò et al.2021 · 4 citations

🤝 Co-authors here

5 co-authors with a page, the most papers together first.

• Hanan Aldarmaki ×3
• Amirbek Djanibekov
• Atharva Kulkarni
• Hawau Olamide Toyin
• Sara Shatnawi

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Arabic Natural Language Processing Conference (ArabicNLP) ×2: ArabicNLP 2023 ×2
• Interspeech: Interspeech 2023
• Actes de la 28e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 3 : Démonstrations

🔗 Cited by

Papers of our library cite their works 46 times (of the 149,439 papers whose bibliographies we read); 29 citing papers with a page here →.

Updated 30 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/ajinkya-kulkarni/