Saurabhchand Bhati

PhD Candidate, ECE JHU.

bhati.jpg

322, Barton Hall

I am a fifth-year Ph.D. student working with the Center for Language and Speech Processing (CLSP) at Johns Hopkins University. My research interests are unsupervised spoken term discovery, unsupervised representation learning and mutlimodal learning. Recently I have been working on jointly learning the segmentation and feature representations. I received B.tech and M.tech in Electrical Engineering from IIT Hyderabad, India, in 2017.

selected publications

  1. Unsupervised Speech Segmentation and Variable Rate Representation Learning using Segmental Contrastive Predictive Coding
    Bhati, Saurabhchand, Villalba, Jesús, Zelasko, Piotr, Moro-Velazquez, Laureano, and Dehak, Najim
    IEEE/ACM Transactions on Audio, Speech, and Language Processing 2022
    PDF
  2. Regularizing Contrastive Predictive Coding for speech applications
    Bhati, Saurabhchand, Villalba, Jesús, Zelasko, Piotr, Moro-Velazquez, Laureano, and Dehak, Najim
    In submission to IEEE/ACM TASLP 2023
    PDF
  3. Segmental SpeechCLIP: Utilizing Pretrained Image-text Models for Audio-Visual Learning
    Bhati, Saurabhchand, Villalba, Jesús, Moro-Velazquez, Laureano, Thebaud, Thomas, and Dehak, Najim
    In submission 2023
    PDF