Publication Details
Study of Probabilistic and Bottle-Neck Features in Multilingual Environment
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Janda Miloš, Ing. (DCGM FIT BUT)
Neural networks, multilingual apeech recognition, Botle-Neck features, probabilistic features
The article studies properties of features obtained using neural networks in milti=lingual recognition systems. The neural networks are trained on particular data and thus it is interesting to observe bahavior of these features when used on data from different language.
This study is focused on the performance of Probabilistic and Bottle-Neck features on different language than they were trained for. It is shown, that such porting is possible and that the features are still competitive to PLP features. Further, several combination techniques are evaluated. The performance of combined features is close to the best performing system. Finally, bigger NNs were trained on large data from different domain. The resulting features outperformed previously trained systems and combination with them further improved the system performance.
@INPROCEEDINGS{FITPUB9764, author = "Franti\v{s}ek Gr\'{e}zl and Martin Karafi\'{a}t and Milo\v{s} Janda", title = "Study of Probabilistic and Bottle-Neck Features in Multilingual Environment", pages = "359--364", booktitle = "Proceedings of ASRU 2011", year = 2011, location = "Hilton Waikoloa Village, Big Island, Hawaii, US", publisher = "IEEE Signal Processing Society", ISBN = "978-1-4673-0366-8", language = "english", url = "https://www.fit.vut.cz/research/publication/9764" }