Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Investigation and Analysis of Hyper and Hypo neuron pruning to selectively update neurons during Unsupervised Adaptation


Jan 06, 2020
Vikramjit Mitra, Horacio Franco

* DSP, 29 pages, 8 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech


May 21, 2019
Emre Yılmaz, Vikramjit Mitra, Ganesh Sivaraman, Horacio Franco

* to appear in Computer Speech & Language - https://doi.org/10.1016/j.csl.2019.05.002 - arXiv admin note: substantial text overlap with arXiv:1807.10948 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Articulatory Features for ASR of Pathological Speech


Jul 28, 2018
Emre Yılmaz, Vikramjit Mitra, Chris Bartels, Horacio Franco

* Accepted for publication at Interspeech 2018 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition


Feb 16, 2018
Vikramjit Mitra, Wen Wang, Chris Bartels, Horacio Franco, Dimitra Vergyri

* 5 pages 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Interpreting DNN output layer activations: A strategy to cope with unseen data in speech recognition


Feb 16, 2018
Vikramjit Mitra, Horacio Franco

* 5 pages. arXiv admin note: substantial text overlap with arXiv:1708.09516 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Leveraging Deep Neural Network Activation Entropy to cope with Unseen Data in Speech Recognition


Aug 31, 2017
Vikramjit Mitra, Horacio Franco

* 7 pages, Index Terms: automatic speech recognition, robust speech recognition, unsupervised adaptation, neural network activations, confidence measures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email