Scholar
Navdeep Jaitly
Google Scholar ID: kjMNMLkAAAAJ
Apple
Citations & Impact
Citations
33,757
H-index
43
i10-index
85
Publications
20
Co-authors
44
list available
Publications
Resume (English only)
Academic Achievements
- - Kaldi Recipe for TIMIT and decoding scripts
- - PhD Thesis: Exploring Deep Learning Methods for Discovering Features in Speech Signals
- - INTERSPEECH 2014 paper and code on how multiframe predictions can significantly improve performance of DNN-HMM systems
- - Paper and presentation slides on creating augmented datasets for training neural networks on audio data (ICML 2013)
- - Work at Google using Deep Neural Networks for Acoustic Modeling (Interspeech 2013)
- - Paper on using an autoencoder with deformable template parts to discover features in speech (NIPS 2011 Workshop)
- - Discovering features in raw speech signals that can be used to achieve high speech recognition accuracy
- - Cryobayes: An algorithm for 3D Reconstruction of Macromolecular Structure from Electron Cryo Microscopy data
- - Decon2LS: A software tool for automatic analysis of high resolution mass spectral data
- - MultiAlign: A software tool for finding mass spectral features common to multiple mass spectral analyses
Research Experience
- Currently working on new Deep Learning models for sequences, inspired by the recent success of sequence-to-sequence, at Google.
Education
- Degree: PhD; Institution: University of Toronto; Advisor: Geoffrey Hinton; Field: Computer Science.
Background
- Research Interests: Machine Learning, Bioinformatics. Background: Recently graduated from the Department of Computer Science at the University of Toronto under the supervision of Geoffrey Hinton. Now a Research Scientist at Google in the Brain team.
Miscellany
- Contact: Email ndjaitly@cs.toronto.edu; Office located at Pratt Bldg, Room 275, Dept of Computer Science, University of Toronto.
