|
|
|
||
Last update: doc. Mgr. Barbora Vidová Hladká, Ph.D. (25.04.2019)
|
|
||
Last update: Mgr. Nino Peterek, Ph.D. (10.06.2019)
For successful completion of course programming of three small projects necessary (speech library functions and a small speech application) and oral exam. |
|
||
Last update: Mgr. Nino Peterek, Ph.D. (11.05.2022)
[JEL] F. Jelinek, Statistical Methods for Speech Recognition, MIT Press, 1998
[PSU] J. Psutka, L. Müller, J. Matoušek, V. Radová, Mluvíme s počítačem česky, Academia, 2006
[SPO] X. Huang, A. Acero, H. Hon, Spoken Language Processing, Prentice-Hall, 2001
[DLA] Dong Yu,Li Deng, Automatic Speech Recognition A Deep Learning Approach, Springer, 2015
[KLW] U. Kamath, J. Liu, J. Whitaker, Deep Learning for NLP and Speech Recognition, Springer, 2019
|
|
||
Last update: Mgr. Nino Peterek, Ph.D. (10.06.2019)
Exam covers presented themes, there is only oral exam. Finalisation of practical part is not necessary before the exam. |
|
||
Last update: Mgr. Nino Peterek, Ph.D. (11.06.2019)
Overview of speech technologies
Acoustic Modelling (SPO C8-C9 | JEL C2-C3 | PSU C5.3 | DLA C3+C6, partially repetition of NPFL038)
Language Modelling (NPFL067 | JEL C4 | SPO C11 | PSU 5.4)
Basic decoding techniques (SPO C12 | JEL C5-C6 | PSU C6)
Large vocabulary search algorithms (SPO C13 | JEL C5-C6 | PSU 6.7.3, 6.7.5, 6.10)
Automatic dialogue systems (SPO C17 | PSU C11)
Speaker identification (PSU C9)
This course can be preceded by NPFL038 and combined with NPFL067, NPFL068, NPFL123. The software tools and libraries will be introduced and trained in the practical part of course. |