. "Moskovskij gosudarstvennyj universitet im. M. V. Lomonosova" . "Moscow" . "674-52-0110-X" . . . "Fonetick\u00E1 segmetnace na b\u00E1zi HMM v prost\u0159ed\u00ED programu Praat"@cs . "HMM-Based Phonetic Segmentation in Praat Environment" . . "Vol\u00EDn, J." . "1"^^ . . "3"^^ . "2007-10-14+02:00"^^ . "RIV/68407700:21230/07:03137073" . . . "537;541" . "Poll\u00E1k, Petr" . "Phonetic segmentation is required in many applications of current speech technologies. One of the most frequently used methods is based on forced alignment of trained Hidden Markov models of phones. This approach is used in our phonetic segmentation tool which is constructed on the basis of HTK toolkit and integrated with the Praat environment. The system is currently used for Czech language and the required input is speech of known content, i.e. with its orthographic record. The system creates regular orthoepic transcription which is obtained by conversion rules. Exceptions from regular pronunciation can be marked by simple syntax so that forced alignment is finally provided on real phonetic contents of the utterance. The system is available for public usage."@en . . "HMM-Based Phonetic Segmentation in Praat Environment"@en . "HMM ASR; Praat; phonetic segmentation"@en . . "21230" . . . . "Phonetic segmentation is required in many applications of current speech technologies. One of the most frequently used methods is based on forced alignment of trained Hidden Markov models of phones. This approach is used in our phonetic segmentation tool which is constructed on the basis of HTK toolkit and integrated with the Praat environment. The system is currently used for Czech language and the required input is speech of known content, i.e. with its orthographic record. The system creates regular orthoepic transcription which is obtained by conversion rules. Exceptions from regular pronunciation can be marked by simple syntax so that forced alignment is finally provided on real phonetic contents of the utterance. The system is available for public usage." . "Skarnitzl, R." . "[03CCBAD30BB6]" . "P(GA102/05/0278), Z(MSM6840770014)" . "424389" . "Moskva" . "The XII International Conference Speech and Computer - SPECOM 2007" . . . "Fonetick\u00E1 segmetnace na b\u00E1zi HMM v prost\u0159ed\u00ED programu Praat"@cs . "HMM-Based Phonetic Segmentation in Praat Environment" . "Fonetick\u00E1 segmentace je po\u017Eadov\u00E1na v mnoha aplikac\u00EDch hlasov\u00FDch technologi\u00ED. Jedna z nej\u010Dast\u011Bji pou\u017E\u00EDvan\u00FDch metod je zalo\u017Eena na aplikaci zarovn\u00E1n\u00ED natr\u00E9novan\u00FDch HMM model\u016F jednotliv\u00FDch element\u00E1rn\u00EDch hl\u00E1sek. Tento p\u0159\u00EDstup byl pou\u017Eit i v realizovan\u00E9m n\u00E1stroji fonetick\u00E9 segmetnace na b\u00E1zi HTK toolkitu, kter\u00FD byl integrov\u00E1n do prost\u0159ed\u00ED programu Praat. Syst\u00E9m je aktu\u00E1ln\u011B k disposici pro \u010De\u0161tinu a po\u017Eadovan\u00FDm vstupem je zn\u00E1m\u00FD obsah promluvy ve form\u011B ortografick\u00E9ho z\u00E1znamu. Z uveden\u00FDch vstupn\u00EDch \u00FAdaj\u016F je vytvo\u0159ena pravideln\u00E1 v\u00FDslovnost z\u00EDskan\u00E1 pomoci pravidel p\u0159ev\u00E1d\u011Bj\u00EDc\u00EDch ortografick\u00FD z\u00E1znam do ortoepick\u00E9 formy. V\u00FDjimky z pravideln\u00E9 v\u00FDslovnosti mohou b\u00FDt vyzna\u010Deny jednoduchou syntax\u00ED v ortografick\u00E9m z\u00E1znamu v interaktivn\u00EDm re\u017Eimu, tak\u017Ee zarovn\u00E1n\u00ED je n\u00E1sledn\u011B realizov\u00E1no pro skute\u010Dn\u00FD obsah promluvy. Uveden\u00FD n\u00E1stroj je voln\u011B dostupn\u00FD."@cs . . . "5"^^ . "RIV/68407700:21230/07:03137073!RIV08-GA0-21230___" . "HMM-Based Phonetic Segmentation in Praat Environment"@en . . .