Semi-supervised phoneme recognition with recurrent ladder networks

Link:
Autor/in:
Erscheinungsjahr:
2017
Medientyp:
Text
Schlagworte:
  • Recurrent neural networks
  • Models
  • Handwriting recognition
  • Speech
  • Speech Recognition
  • Phoneme recognition
  • Ladder networks
  • Semi-supervised learning
  • Recurrent neural networks
  • Models
  • Handwriting recognition
  • Speech
  • Speech Recognition
Beschreibung:
  • Ladder networks are a notable new concept in the field of semi-supervised learning by showing state-of-the-art results in image recognition tasks while being compatible with many existing neural architectures. We present the recurrent ladder network, a novel modification of the ladder network, for semi-supervised learning of recurrent neural networks which we evaluate with a phoneme recognition task on the TIMIT corpus. Our results show that the model is able to consistently outperform the baseline and achieve fully-supervised baseline performance with only 75% of all labels which demonstrates that the model is capable of using unsupervised data as an effective regulariser.
Lizenz:
  • info:eu-repo/semantics/restrictedAccess
Quellsystem:
Forschungsinformationssystem der UHH
Interne Metadaten
Quelldatensatz
oai:www.edit.fis.uni-hamburg.de:publications/dde1412c-ea81-4f73-a6a3-44feefbf46a0