A novel pyramidal-FSMN architecture with lattice-free MMI for speech recognition

26 Oct 2018 Xuerui Yang Jiwei Li Xi Zhou

Deep Feedforward Sequential Memory Network (DFSMN) has shown superior performance on speech recognition tasks. Based on this work, we propose a novel network architecture which introduces pyramidal memory structure to represent various context information in different layers... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Categories


  • SOUND
  • AUDIO AND SPEECH PROCESSING