About Me
Maulik Madhavi has worked in speech signal processing since 2010. He earned his Ph.D. in Information and Communication Systems from DA-IICT, Gandhinagar, India, in 2017, and completed his M.Tech. in ICT (Communication Systems) at the same institute.
He contributed to a DeIT-sponsored national research project on prosodically guided phonetic search for Indian language speech databases and served as a teaching assistant for eight undergraduate and graduate courses during his master’s and doctoral studies.
From 2017 to 2021, he was a Research Fellow at the National University of Singapore, mentoring graduate students and conducting research on spoken-dialogue systems for autonomous vehicles and speech recognition for healthcare.
Since 2021, he has been a Video Analytics Researcher at NCS Pte. Ltd., working on generative AI for vision systems. He contributes to the in-house no-code platform KaICC, developing algorithms for vision model training and inference.
He received an IAPR travel scholarship to present his work at the International Conference on Biometrics (ICB 2012) in New Delhi, India.
Research Interests
- Spoken information retrieval
- Applications of spoken language technology
- Spoken language understanding
- Vision language system
- Deep learning model optimization for inference speed and accuracy
Research Keywords
- Speech signal processing
- Speech information retrieval (spoken term detection)
- Dialogue understanding
- Technology for spoken language processing
- Feature indexing for large-scale search
- Vision-language perception
- Object detection
- Image recognition
Tools
- Programming Languages:
- ML Frameworks:
- LLM Tools:
- ML Tools:
- Deployment Tools:
- Web Frameworks:
