“Approaches to convert RNNLM to BNLM”版本间的差异
来自cslt Wiki
（→related paper） |
|||
| 第3行： | 第3行： | ||
=related paper= | =related paper= | ||
* VARIATIONAL APPROXIMATION OF LONG-SPAN LANGUAGE MODELS FOR LVCSR[http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5947612&tag=1] | * VARIATIONAL APPROXIMATION OF LONG-SPAN LANGUAGE MODELS FOR LVCSR[http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5947612&tag=1] | ||
| + | * Conversion of Recurrent Neural Network Language Models to Weighted Finite State Transducers for Automatic Speech Recognition[http://people.irisa.fr/Gwenole.Lecorve/pdf/lecorve12c.pdf] | ||
2014年11月2日 (日) 07:34的版本
main paper
comparing approaches to convert recurrent neural networks into backoff language models for efficient decoding[1]
