From cslt Wiki
- LM count files still undelivered!
- sparse DNN: sticky training (retrain the nnet while keeping the sparsness)
zero small values(test set: 1900), with extremely sparseness:
|without sticky: WER||7.55||9.46||53.23||98.99||-|
|with sticky: WER||7.55||7.56||7.87||8.81||9.87|
Conclusion: The extremely sparse network can largely pertain the performance of DNN. The structure seems more important than the parameter tuning based on the structure.
- fixed-point DNN forwarding
- working on migrating the Atlas lib to ARM.
- working on atlas/mkl independent implementation.
- 6000h model training, could be finished on 25th approximately.
- working on sequential DNN DT: refer to "Error Back Propagation For Sequence Training of Context-Dependent Deep Networks For Conversation Speech Transcription"
GPU & CPU merge
- on progress.
RNN LM progress
- Initial work started. 100M data with a 10k vocabulary obtained a perplexity 180.
- More exploration continuous.
- check the reference, and change the compiling options
- the large-scale AM training based on the Tencent 400h data is done, continuous HMM.
- To be done
- large scale parallel training.
- NN based engine(dynamic and static).
- Semi-continuous model with the Tencent data
- Debug on external an ARM board.