Contact | Education | Research and publications | Thesis | Professional | Teaching | Other skills | PDFPDF 

Research and publications

Publications

  1. Phoebe: Pronunciation-aware Contextualization for End-to-end Speech Recognition
  2. Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
  3. Model Unit Exploration for Sequence-to-Sequence Speech Recognition
  4. Dictionary Augmented Sequence-to-Sequence Neural Network for Grapheme to Phoneme prediction
  5. Sequence-to-Sequence Neural Network Model with 2D Attention for Learning Japanese Pitch Accents
  6. Pronunciation learning with RNN-transducers
  7. Learning Personalized Pronunciations for Contact Name Recognition
  8. NN-grams: Unifying neural network and n-gram language models for speech recognition
  9. On the compression of recurrent neural networks with an application to LVCSR acoustic modeling for embedded speech recognition
  10. Optimizing OPC data sampling based on orthogonal vector space
  11. Exploring the Nature of Trader Intuition
  12. Model-based scanner tuning in a manufacturing environment
  13. Investigating signal integration with canonical correlation analysis of fMRI brain activation data
  14. Human imagination in financial markets with insiders
  15. A Mind for the Market: an fMRI Study of Attribution of Mental States to Financial Markets
  16. SCR Recording During fMRI Acquisition

Patents

  1. Date and/or time resolution
  2. Learning personalized entity pronunciations
  3. Information matrix creation and calibration test pattern selection based on computational lithography model parameter
  4. Calibration pattern selection based on noise sensitivity
  5. Harmonic resist model for use in a lithographic apparatus and a device manufacturing method

Note: Additional US patent applications under review (closed to the general public).