author: pavel mautner

Text, Speech and Dialogue: 8th International Conference, TSD 2005, Karlovy Vary, Czech Republic, September 12-15, 2005, Proceedings

Text, Speech and Dialogue: 8th International Conference, TSD 2005, Karlovy Vary, Czech Republic, September 12-15, 2005, Proceedings
Václav MatoušekPavel MautnerTomáš Pavelka
Computers
... sentences. Information questions almost always are formed by full sentences. Repair initiations are different. Clarification is formed mostly by phrases. Reformulation and misunderstanding use full sentences in half of the cases and phrases ...
Text, Speech and Dialogue: Second International Workshop, TSD'99 Plzen, Czech Republic, September 13-17, 1999, Proceedings

Text, Speech and Dialogue: Second International Workshop, TSD'99 Plzen, Czech Republic, September 13-17, 1999, Proceedings
Vaclav MatousekPavel MautnerJana OcelikovaPetr Sojka
Technology Engineering
... pronunciation dictionaries : - the Onomastica pronunciation dictionary consisting of 233.919 names ; for names with ... success rate. - S5 pronunciation dictionary : 8.480 words . 6 Results The phonemisation errors were determined by ...
Text, Speech and Dialogue: Second International Workshop, TSD'99 Plzen, Czech Republic, September 13-17, 1999, Proceedings

Text, Speech and Dialogue: Second International Workshop, TSD'99 Plzen, Czech Republic, September 13-17, 1999, Proceedings
Vaclav MatousekPavel MautnerJana OcelikovaPetr Sojka
Technology Engineering
... (matka.Addr) ((Jirka.ELID.Act) pˇrij ́ıt.Pat (dom ̊u.Dir) (vcas-Temp) (10) Rodice zádali Jirku nechodit tam. Parents ... Milan (Has-met Jirku?) Milan George?) Met-Masc. (12) (Milan.Act.ELID) potkat (Jirka.Pat.ELID) In cases (i) through ...
Text, Speech and Dialogue: 10th International Conference, TSD 2007, Pilsen, Czech Republic, September 3-7, 2007, Proceedings

Text, Speech and Dialogue: 10th International Conference, TSD 2007, Pilsen, Czech Republic, September 3-7, 2007, Proceedings
Václav MatoušekPavel Mautner
Computers
... 40k and 60k words (OOV: out of vocabulary word rate; WER: word error rate; MAP: mean average precision) OOV WER MAP – Text 0.4475 20k general LM 6.77% 24.2% 0.3013 20k topic LM 3.27% 20.3% 0.3412 20k interpolated LM 3.27% 19.6% 0.3393 ...
Text, Speech and Dialogue: 12th International Conference, TSD 2009, Pilsen, Czech Republic, September 13-17, 2009. Proceedings

Text, Speech and Dialogue: 12th International Conference, TSD 2009, Pilsen, Czech Republic, September 13-17, 2009. Proceedings
Vaclav MatousekPavel Mautner
Language Arts Disciplines
... InfP, noun phrases NP, prepositionaladjective phrases PrepAdjP, prepositional-nominative phrases PrepNP, clauses SentP and reflexive marker sie ̧. Arguments can be parametrised. AdvP has no parameters, the only parameter of AdjP and NP ...

© 2024 www.zuuk.org. All rights reserved.

This website uses cookies and collects data for optimal performance. Your continued use signifies agreement to our Privacy Policy.