. "0302-9743" . "Spoken Dialogue System Design in 3 Weeks"@en . "Lecture Notes in Artificial Intelligence" . "Spoken Dialogue System Design in 3 Weeks" . "Spoken Dialogue System Design in 3 Weeks" . . . "\u0160m\u00EDdl, Lubo\u0161" . "Neuveden" . . "10.1007/978-3-642-32790-2_76" . . "3"^^ . "RIV/49777513:23520/12:43916099!RIV13-MSM-23520___" . . "8"^^ . "Spoken Dialogue System Design in 3 Weeks"@en . "3"^^ . . "RIV/49777513:23520/12:43916099" . . "This article describes knowledge-based spoken dialogue system design from scratch. It covers all stages which were performed during the period of three weeks: definition of semantic goals and entities, data collection and recording of sample dialogues, data annotation, parser and grammars design, dialogue manager design and testing. The work was focused mainly on rapid development of such a dialogue system. The final implementation was written in dynamically generated VoiceXML. The large vocabulary continuous speech recognition system was used and the language understanding module was implemented using non-recursive probabilistic context free grammars which were converted to finite states transducers. The design and implementation has been verified on a railway information service task with a real large-scale database. The paper describes an innovative combination of data, expert knowledge and state-of-the-art methods which allow fast spoken dialogue system design." . . . . . . "This article describes knowledge-based spoken dialogue system design from scratch. It covers all stages which were performed during the period of three weeks: definition of semantic goals and entities, data collection and recording of sample dialogues, data annotation, parser and grammars design, dialogue manager design and testing. The work was focused mainly on rapid development of such a dialogue system. The final implementation was written in dynamically generated VoiceXML. The large vocabulary continuous speech recognition system was used and the language understanding module was implemented using non-recursive probabilistic context free grammars which were converted to finite states transducers. The design and implementation has been verified on a railway information service task with a real large-scale database. The paper describes an innovative combination of data, expert knowledge and state-of-the-art methods which allow fast spoken dialogue system design."@en . "170489" . "[338360B6EF31]" . "DE - Spolkov\u00E1 republika N\u011Bmecko" . . . . . "7499" . "P(ED1.1.00/02.0090), P(TE01020197), S" . "Valenta, Tom\u00E1\u0161" . "\u0160vec, Jan" . . "23520" . . "spoken dialogue systems, language understanding, VoiceXML"@en . "http://link.springer.com/chapter/10.1007%2F978-3-642-32790-2_76" . .