Skip to content



Please note that some of the published papers may be copyrighted by the respective publishing organizations, such as IEEE, Elsevier, and Wiley etc. as cited. You are advised to contact the publishing organization for final versions of the papers.


  • Granted US10878807B2: "System and method for implementing a vocal user interface by combining a speech to text system and a speech to intent system". [Also granted in Europe]
  • Granted US11049495B2: "Method and device for automatically learning relevance of words in a speech recognition system"
  • Approved for grant US20210056958A1: "System and method for tone recognition in spoken languages"
  • Approved for grant US20210055778A1: "A low-power keyword spotting system"
  • Application WO2021030918A1: "User-defined keyword spotting"
  • Application WO2021226709A1: "Neural architecture search with imitation learning"

Ph.D. Thesis

Vikrant Singh Tomar, McGill University, "Discriminative Manifold Learning for Automatic Speech Recognition".


Other Publications/Reports