Aswin Shanmugam Subramanian

Aswin Shanmugam Subramanian
  • Biography

    PhD, Johns Hopkins University, 2022.

    Bio – Aswin's current research interests are audio signal processing and end-to-end speech recognition. At Johns Hopkins, his doctoral research focused on improving far-field speech recognition with front-end processing like denoising, dereverberation, localization, and source separation.

  • MERL Publications

    •  Venkatesh, S., Wichern, G., Subramanian, A.S., Le Roux, J., "Disentangled surrogate task learning for improved domain generalization in unsupervised anomolous sound detection," Tech. Rep. TR2022-092, Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge 2022, July 2022.
      BibTeX TR2022-092 PDF
      • @techreport{Venkatesh2022jul,
      • author = {Venkatesh, Satvik and Wichern, Gordon and Subramanian, Aswin Shanmugam and Le Roux, Jonathan},
      • title = {Disentangled surrogate task learning for improved domain generalization in unsupervised anomolous sound detection},
      • institution = {DCASE2022 Challenge},
      • year = 2022,
      • month = jul,
      • url = {https://www.merl.com/publications/TR2022-092}
      • }