This paper proposes a learning speed improvement using multi-GPUs on DNN-based acoustic model training in Korean intelligent personal assistant (IPA). DNN learning involves iterative, stochastic parameter updates. These updates depend on the previous updates. The proposed method provides a distributed computing for DNN learning. DNN-based acoustic models are trained by using 320 h length Korean speech corpus. It was shown that the learning speed becomes five times faster on this implementation while maintaining speech recognition rate.
CITATION STYLE
Lee, D., Kim, K. H., Kang, H. E., Wang, S. H., Park, S. Y., & Kim, J. H. (2015). Learning speed improvement using multi-GPUs on DNN-based acoustic model training in Korean intelligent personal assistant. In Natural Language Dialog Systems and Intelligent Assistants (pp. 263–271). Springer International Publishing. https://doi.org/10.1007/978-3-319-19291-8_27
Mendeley helps you to discover research relevant for your work.