Daniel Povey

Assistant Research Professor

Primary Appointment: Center for Language and Speech Processing

Research Interests

  • Acoustic Modeling
  • Pronunciation and stress modeling
  • Deep neural networks
  • Language modeling
  • Weighted Finite State Transducers

Daniel Povey completed his PhD at Cambridge University in 2003, and after spending just under ten years working for industry research labs (IBM Research and then Microsoft Research), joined Johns Hopkins University in 2012. He is best known as the main developer of Kaldi, the popular speech recognition toolkit. His thesis work introduced several practical innovations for discriminative training of models for speech recognition, and made those techniques widely popular. His current work mostly relates to Deep Neural Networks and their application to speech recognition.

Center for Language and Speech Processing