Filip Jurčíček

Main Research Interests

I am interested in development of natural, responsive, and adaptive dialogue systems. This for example includes:

  • Automatic speech recognition
  • Semantic parsing
  • Dialogue management
  • Natural language generation

I focus on statistical methods to resolve the inherent uncertainty in spoken speech. My main research interests lie in applying reinforcement learning and machine learning techniques, in general, to dialogue management and natural language processing.



2015-12-21 Ondrej Klejch (an M.Sc. student of mine) has got the CZ.NIC aword for his master thesis in ACM-SPY Czech republic. For more details see: and

2015-09-04 We have sucessfully organised Sigdial 2015. We had a record breaking number of attendees - 149! I thank to all the people who helped me - especially all my students.

2015-07-01 Preparing Sigdial 2015 organised by UFAL. More details can be found at

2015-02-03 Martin Vejman (an M.Sc. student of mine) entered the MTA Now York compettion with his Alex: public transport information system (in English). 

2015-01-28 Given an interview for

2014-06-28 Given a lecture at Festival fantazie at Chotěboř, Czech Republic.

2014-04-04 Given an interview at radio Leonardo:

2014-01-15 Attending Information and networking days - H2020 Work Programme 2014-2015, Connecting Europe Facility​, My slides can be found at

2013-10-24 Article about my work in FORUM UK: "Opustil Cambridge, aby v Praze učil počítače komunikovat hlasem."

2013-05-26 Appeared in MF DNES: "Česko láká vědce: Vraťte se do vlasti."


Curriculum Vitae

I have been with Charles University in Prague since September 2011. Currently, I am an assistant professor at the  Institute of Formal and Applied Linguistics. Before joining Charles University, I worked as a research associate at Cambridge University. My work involved development of statistical methods for spoken dialogue management, in particular POMDPs (Partially-Observable Markov Decision Processes). Prior that I worked as a software consultant in IT industry. I participated in projects implementing internet/IP telephony and automation of customer services. I received my PhD degree in 2007 from the department of Computer Science at the University of West Bohemia in Pilsen (Czech Republic) on the subject of semantic parsing for spoken dialogue systems. During my PhD studies, I spent 10 months as a visiting scholar in the Center for Language and Speech Processing at The Johns Hopkins University (USA). 


List of classes

Selected Bibliography


F. Jurčíček, B. Thomson, S. Young: Reinforcement learning for parameter estimation in statistical spoken dialogue systems. (GS)
In: Computer Speech and Language, 3, June 2012.

F. Jurčíček, B. Thomson, S. Young: Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs. (GS
In: ACM Trans. Speech Lang. Process., June 2011.

F. Jurčíček, J. Pradlová: "Chyby" grafických kalkulátorů aneb ne vše, co je viděno, je pravda a ne vše, co je pravda, je viděno. (GS)
In: Matematika - fyzika - informatika, 10, 1999.

Book chapters

M. Gašić, F. Jurčíček, B. Thomson, S. Young: Optimisation for POMDP-Based Spoken Dialogue Systems. (GS)
In: Data-driven methods for adaptive Spoken Dialogue Systems, 2012.

James Henderson, F. Jurčíček: Data-Driven Methods for Spoken Language Understanding. (GS)
In: Data-driven methods for adaptive Spoken Dialogue Systems, 2012.

Peer-reviewed conferences

O. Klejch, O. Plátek, L. Žilka, F. Jurčíček: CloudASR: Platform and Service. (GS)
In: TSD '15: Proc. of the 18th Int. Conf. on Text, Speech and Dialogue, 9302, 2015. 

L. Žilka, F. Jurčíček: Incremental LSTM-based Dialog State Tracker. (GS)
In: IEEE ASRU '15: Proceedings of ASRU, Phoenix, AZ, USA, 2015. 

O. Dušek, F. Jurčíček: Training a Natural Language Generator From Unaligned Data. (GS)
In: ACL '15, Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2015. 

O. Dušek, O. Plátek, L. Žilka, F. Jurčíček: Alex: Bootstrapping a Spoken Dialogue System for a New Domain by Real Users. (GS)
In: SIGDIAL '14: Proc. of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Philadelphia, USA, 2014.

O. Plátek, F. Jurčíček: Free on-line speech recogniser based on Kaldi ASR toolkit producing word posterior lattices. (GS)
In: SIGDIAL '14: Proc. of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Philadelphia, USA, 2014.

M. Korvas, O. Plátek, O. Dušek, L. Žilka, F. Jurčíček: Free English and Czech telephone speech corpus shared under the CC-BY-SA 3.0 license. (GS)
In: LREC '14: Proc. of the 9th International Conference on Language Resources and Evaluation, Reykjavik, Iceland, 2014.

Lukáš Žilka, David Marek, Matěj Korvas, F. Jurčíček: Comparison of Bayesian Discriminative and Generative Models for Dialogue State Tracking. (GS)
In: SIGDIAL '13: Proc. of the 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Metz, France, 2013.

Ondřej Dušek, F. Jurčíček: Robust Multilingual Statistical Morphological Generation Models. (GS)
In: Proc. ACL Student Research Workshop, Sofia, Bulgaria, 2013. 

F. Jurčíček: Reinforcement learning for spoken dialogue systems using off-policy natural gradient method. (GS)
In: IEEE SLT '12: Proc. IEEE Spoken Language Technology Workshop, Miami, USA, 2012.

F. Jurčíček, S. Keizer, M. Gašić, F. Mairesse, B. Thomson, K. Yu, S. Young: Real user evaluation of spoken dialogue systems using Amazon Mechanical Turk. (GS)
In: Proc. Interspeech, Florence, Italy, 2011.

F. Jurčíček, B. Thomson, S. Keizer, F. Mairesse, M. Gašić, K. Yu, S. Young: Natural Belief-Critic: a reinforcement algorithm for parameter estimation in statistical spoken dialogue systems. (GSIn: Proc. Interspeech, Tokyo, Japan, 2010. (Best paper award)

B. Thomson, F. Jurčíček, M. Gašić, S. Keizer, F. Mairesse, K. Yu, S. Young: Parameter learning for POMDP spoken dialogue models. (GS)
In: IEEE SLT '10: Spoken Language Technology Workshop, 2010. (Best paper award)