"Returnn: The RWTH extensible training framework for universal recurrent ..."

Patrick Doetsch et al. (2017)

> Home

Details and statistics

DOI: 10.1109/ICASSP.2017.7953177

access: closed

type: Conference or Workshop Paper

metadata version: 2022-12-07

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/icassp/DoetschZVKSN17
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/icassp/DoetschZVKSN17
Patrick Doetsch, Albert Zeyer, Paul Voigtlaender, Ilia Kulikov, Ralf Schlüter, Hermann Ney:
Returnn: The RWTH extensible training framework for universal recurrent neural networks. ICASSP 2017: 5345-5349

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.