nike

Sameer Khurana MIT

PhD Student, Massachusetts institute of technology
Doctoral Researcher, MIT Computer science and Artificial intelligence Laboratory (CSAIL)
skhurana at mit dot edu
Linkedin     Github     Google Scholar

I am a doctoral researcher in Artificial Intelligence at MIT CSAIL. I work on Self-Supervised machine learning and Cross-Lingual Transfer Learning for spoken language technologies such as Speech Recognition and Speech Translation with Dr. James Glass.

Work Experience

Check out my Linkedin page.

Publications

  • SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation
    Sameer Khurana, Antoine Laurent, James Glass, Preprint '22 [Paper]

  • CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification
    Yuan Gong, Sameer Khurana, Andrew Rouditchenko, James Glass, Preprint '22 [Paper]

  • Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0
    Sameer Khurana, Antoine Laurent, James Glass, ICASSP '21 [Paper]

  • PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
    Cheng-I Jeff Lai, Yang Zhang, Alexander H Liu, Shiyu Chang, Yi-Lun Liao, Yung-Sung Chuang, Kaizhi Qian, Sameer Khurana, David Cox, James Glass, NeurIPS '21 [Paper]

  • Unsupervised domain adaptation for speech recognition via uncertainty driven self-training
    Sameer Khurana, Niko Moritz, Takaaki Hori, Jonathan Le Roux, ICASSP '21 [Paper]

  • Cstnet: Contrastive speech translation network for self-supervised speech representation learning
    Sameer Khurana, Antoine Laurent, James Glass, Preprint '20 [Paper]

  • A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning
    Sameer Khurana, Antoine Laurent, Wei-Ning Hsu et. al, Interspeech, 2020 [Paper]

  • Robust Training of Vector Quantized Bottleneck Models,
    Adrian Lancucki, Jan Chorowski, Guillaume Sanchez, Ricard Marxer, Nanxin Chen, Hans J.G.A. Dolfing, Sameer Khurana, Tanel Alumae, Antoine Laurent, IJCNN, 2020 [Paper]

  • Unsupervised Neural Segmentation and Clustering for Unit Discovery in Sequential Data,
    Generative Reasoning Workshop, NeurIPS 2019

  • A Fatorial Deep Markov Model For Unsupervised Disentangled Representation Learning From Speech,
    Khurana, S., Joty, S., Ali, A., & Glass J. (2019), ICASSP 2019. [Paper]

  • DeepSol: A Deep Learning Framework for Sequence-Based Protein Solubility Prediction.
    Khurana, S., Rawi, R., Kunji, K., & Chuang, G. Y., Bensmail, H., Mall, R. (2018). Bioinformatics.. [Article] [Code]

  • Najafian, M., Khurana, S., Shon, S., Ali, A., & Glass, J. (2018). Exploiting convolutional neural networks for phonotactic based dialect identification, International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018

  • Khurana, S., Najafian, M., Ali, A., Hanai, T.A., Belinkov, Y., Glass, J. (2017) QMDIS: QCRI-MIT Advanced Dialect Identification System. Proc. Interspeech 2017, Stockholm, Sweden. [Paper]

  • Ali, A., Dehak, N., Cardinal, P., Khurana, S., Yella, S.H., Glass, J., Bell, P., Renals, S. (2016) Automatic Dialect Detection in Arabic Broadcast Speech. Proc. Interspeech 2016. 2934-2938. San Francisco. [Paper]

  • Khurana, S., Ali, A. (2016) QCRI Advanced Transcription System (QATS) for the Arabic Multi-Dialect Broadcast Media Recognition: MGB-2 Challenge. Spoken Language Technology Workshop, IEEE 2016 San Diego, United States. [Paper]

  • Dalvi, F., Zhang, Y., Khurana, S., Durrani, N., Sajjad, H, Abdelali, A., Mubarak, H., Ali, A., Vogel, S. (2017) QCRI Live Speech Translation System. 15th Conference of the European Chapter of the Association for Computational Linguistics. Valencia. [Paper]

    •