Maulik Madhavi
Video Analytics Researcher building generative-AI vision systems — with a decade in speech & dialogue.
30+
Publications
15+ yrs
In speech & vision
PhD
DA-IICT, 2017
NUS
Research Fellow (2017–21)
What I do
Vision × Language
Multimodal perception, object detection, image recognition, and generative-AI vision systems.
Speech & Dialogue
Spoken term detection, spoken language understanding, and dialogue systems for real-world deployments.
Model Efficiency
Deep-learning model optimization for inference speed and accuracy on edge and server.
Recent publications
- B. Sharma, M. Madhavi, X. Zhou, H. Li. “Exploring teacher-student learning approach for multi-lingual speech-to-intent classification,” IEEE ASRU, 2021.
- R. Das, M. Madhavi, H. Li. “Diagnosis of COVID-19 using Auditory Acoustic Cues,” Interspeech, 2021.
- X. Qian, M. Madhavi, Z. Pan, J. Wang, H. Li. “Multi-target DoA estimation with an audio-visual fusion mechanism,” ICASSP, 2021.