Sindhu B. Hegde

Verisk Analytics | IIIT Hyderabad

Hi! I am a Machine Learning Researcher @ Verisk Analytics, with an immense interest and enthusiasm in the areas of Computer Vision & AI.

Prior to joining Verisk, I pursued Masters’ by Research (MS) at Centre for Visual Information Technology (CVIT), IIIT Hyderabad supervised by Prof. C V Jawahar (IIIT-H) and Prof. Vinay Namboodiri (University of Bath, UK). My Masters’ research focused on exploiting the redundancies in vision and speech modalities for cross-modal generation.

Research interests: Computer Vision, Machine Learning, Deep Learning, Speech Processing, Multi-modal Learning: Vision + Speech/Language

News [Archive]

Aug 2022 Accepted the PhD offer from University of Oxford! Excited to join the Visual Geometry Group (VGG), with Prof. Andrew Zisserman from October 2022!
Jul 2022 2 papers accepted to ACM-MM 2022!
1] Talking-Face Video Upsampling 2] Lip-to-Speech Synthesis
May 2022 Successfully defended MS thesis :smile:
Thesis: Exploiting Cross-Modal Redundancy for Audio-Visual Generation
Apr 2022 Promoted to Lead Data Scientist at Verisk Analytics
Feb 2022 Participated in Research Week with Google. Got a chance to interact with amazing researchers all over the world!

Recent papers [Full list]

  1. ACM-MM
    Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors
    Hegde, Sindhu, Mukhopadhyay, Rudrabha, Namboodiri, Vinay P, and Jawahar, CV
    In Proceedings of the 30th ACM International Conference on Multimedia (MM’22) 2022
  2. ACM-MM
    Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
    Hegde, Sindhu, Prajwal, KR, Mukhopadhyay, Rudrabha, Namboodiri, Vinay P, and Jawahar, CV
    In Proceedings of the 30th ACM International Conference on Multimedia (MM’22) 2022