Maximum-likelihood normalization of features increases the robustness of neural-based spoken human-computer interaction

Edmondo Trentin. Maximum-likelihood normalization of features increases the robustness of neural-based spoken human-computer interaction. Pattern Recognition Letters, 66:71-80, 2015. [doi]

@article{Trentin15,
  title = {Maximum-likelihood normalization of features increases the robustness of neural-based spoken human-computer interaction},
  author = {Edmondo Trentin},
  year = {2015},
  doi = {10.1016/j.patrec.2015.07.003},
  url = {http://dx.doi.org/10.1016/j.patrec.2015.07.003},
  researchr = {https://researchr.org/publication/Trentin15},
  cites = {0},
  citedby = {0},
  journal = {Pattern Recognition Letters},
  volume = {66},
  pages = {71-80},
}