• Home
  • About
  • Research
  • Blog
  • Resources
  • Contact

Research

My peer-reviewed publications.

Deep Neural Networks

  • Bridgeout
    Bridgeout: stochastic bridge regularization of deep neural networks
    Training deep neural networks with fewer training samples

Neuro-musculoskeletal Simulation

  • Prediction of muscle activations for reaching movements using deep neural networks
  • francois2018
    Towards finite-element simulation using deep learning

Statistical Speech Synthesis

  • Optimal state duration assignment in hidden Markov model-based text-to-speech synthesis system
    An algorithm for state duration assignment is derived so as to maximise the probability of the state sequence while satisfying all the constraints.
  • Singing Voice Synthesis Using HMM Based TTS and MusicXML
    Describes an SVS system which uses a MusicXML based music score editor for entry of the notes and lyrics to be synthesized and an HMM-based text-to-speech synthesis system as the back-end synthesizer.
  • HMM Based Duration Control for Singing TTS
    A duration control model based on the syllabic analysis of the lyrics is applied to adapt speech-trained duration models to singing duration models

Music Score

  • Development of a Music Score Editor based on MusicXML
    This paper presents a brief description of the structure of the MusicXML format and describes the development of a music score editor based on MusicXML.

© 2016 Najeeb Khan. All Rights Reserved | Adapted from W3layouts