Abstract | ||
---|---|---|
The work by Hinton et al shows that the dropout strategy can greatly improve the performance of neural networks as well as reducing the influence of over-fitting. Nevertheless, there is still not a more detailed study on this strategy. In addition, the effectiveness of dropout on the task of LVCSR has not been analyzed. In this paper, we attempt to make a further discussion on the dropout strategy. The impacts on performance of different dropout probabilities for phone recognition task are experimented on TIMIT. To get an in-depth understanding of dropout, experiments of dropout testing are designed from the perspective of model averaging. The effectiveness of dropout is analyzed on a LVCSR task. Results show that the method of dropout fine-tuning combined with standard back-propagation gives significant performance improvements. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICASSP.2013.6639144 | ICASSP |
Keywords | Field | DocType |
deep neural networks,dropout strategy,lvcsr,speech recognition,large vocabulary continuous speech recognition,timit,dropout,standard backpropagation,model averaging,dropout fine-tuning method,over-fitting influence reduction,backpropagation,dropout probabilities,dropout testing,phone recognition task,neural network performance improvement,neural nets,probability,vectors,testing,neural networks,hidden markov models,accuracy | TIMIT,Computer science,Speech recognition,Phone,Artificial intelligence,Artificial neural network,Backpropagation,Machine learning | Conference |
Volume | Issue | ISSN |
null | null | 1520-6149 |
Citations | PageRank | References |
8 | 0.74 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jie Li | 1 | 9 | 1.70 |
Xiaorui Wang | 2 | 19 | 6.13 |
Bo Xu | 3 | 241 | 36.59 |