Education & Experience

Work Experience

Jul 2025 – Ongoing

Contributed to the development of a 100+ hour dialectal speech corpus for automatic speech recognition (ASR) systems and carried out socio-phonetic analysis for variation and dialect studies.
Defined phonological, morphological, and syntactic rules for large-scale Malayalam data preparation, including clause boundary detection, anaphora resolution, and discourse connectives.
Processed and curated a 300K-token Malayalam corpus for POS, chunking, NER tagging and ensured quality and consistency for LLM training.
Developed a 170K-word Malayalam lexical dictionary with systematic rule-based validation and quality assurance.

Oct 2023 – Nov 2023

Conducted data annotation and segmentation for Mundari, a Munda language of the Austroasiatic family, using Praat.
Performed detailed acoustic and auditory analyses of speech data to identify key linguistic features.
Supported language documentation efforts by analyzing phonetic and phonological patterns.