Sameer Khurana
Massachusetts Institute of Technology
32 Papers
56 Citations
Sameer Khurana is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 9, co-authored 21 publications. Previous affiliations of Sameer Khurana include Qatar Computing Research Institute & Khalifa University.
Chat about Author
Papers
DeepSol: A Deep Learning Framework for Sequence-Based Protein Solubility Prediction
TL;DR: The superior prediction accuracy of DeepSol allows to screen for sequences with enhanced production capacity and can more reliably predict solubility of novel proteins.
209
Automatic Dialect Detection in Arabic Broadcast Speech
Ahmed Ali,Najim Dehak,Najim Dehak,Patrick Cardinal,Sameer Khurana,Sree Harsha Yella,James Glass,Peter Bell,Steve Renals +8 more
- 12 Sep 2016
TL;DR: This work investigates different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework, and combined these features using a multi-class Support Vector Machine (SVM).
•Posted Content
Automatic Dialect Detection in Arabic Broadcast Speech
Ahmed Ali,Najim Dehak,Najim Dehak,Patrick Cardinal,Sameer Khurana,Sree Harsha Yella,James Glass,Peter Bell,Steve Renals +8 more
TL;DR: In this paper, the authors investigated different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework.
83
QCRI advanced transcription system (QATS) for the Arabic Multi-Dialect Broadcast media recognition: MGB-2 challenge
Sameer Khurana,Ahmed Ali +1 more
- 01 Dec 2016
TL;DR: QCRI's speech transcription system for the 2016 Dialectal Arabic Multi-Genre Broadcast (MGB-2) challenge achieved the lowest WER of 14.2% among the nine participating teams.
64
Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training
Sameer Khurana,Niko Moritz,Takaaki Hori,Jonathan Le Roux +3 more
- 06 Jun 2021
TL;DR: In this article, a dropout-based uncertainty-driven self-training technique is proposed for domain adaptation, which uses agreement between multiple predictions obtained for different dropout settings to measure the model's uncertainty about its prediction.
47