Sequence training of multi-task acoustic models using meta-state labels

Olivier Siohan. Sequence training of multi-task acoustic models using meta-state labels. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016. pages 5425-5429, IEEE, 2016. [doi]

@inproceedings{Siohan16,
  title = {Sequence training of multi-task acoustic models using meta-state labels},
  author = {Olivier Siohan},
  year = {2016},
  doi = {10.1109/ICASSP.2016.7472714},
  url = {http://dx.doi.org/10.1109/ICASSP.2016.7472714},
  researchr = {https://researchr.org/publication/Siohan16},
  cites = {0},
  citedby = {0},
  pages = {5425-5429},
  booktitle = {2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016},
  publisher = {IEEE},
  isbn = {978-1-4799-9988-0},
}