Resume
Academic Achievements
- Published numerous papers at top venues including EMNLP, ICLR, IWSLT, LREC-COLING, and INTERSPEECH
- PhD thesis titled 'Overcoming Vocabulary Challenges in Natural Language Processing' focused on open-vocabulary NLP
- Contributed to the BLOOM project (176B-parameter open-access multilingual language model)
- Co-developed BibleTTS, a large high-fidelity multilingual speech corpus
- Contributed to UniMorph 4.0: Universal Morphology
- Paper 'Language Modelling with Pixels' (ICLR 2023) recognized as a notable top-5% submission