|
|
Speech Recognition For Selected Languages
Schmitt, Jan ; Karafiát, Martin (referee) ; Janda, Miloš (advisor)
This bachelor's thesis deals with recognition of continues speech for three languages - Bulgarian, Croatian and Swedish. There are described basics of speech processing and recognition methods like acoustic modeling using hidden Markov models and gaussian mixture models. Another aim of this work is preparing data for those languages from GlobalPhone database, so they may be used with speech recognition toolkits Kaldi and HTK. With data prepared there are several models trained and tested using Kaldi toolkit.
|
|
|
Low-Resource Neural Machine Translation
Filo, Denis ; Fajčík, Martin (referee) ; Jon, Josef (advisor)
This thesis deals with neural machine translation (NMT) for low-resource languages. The goal was to evaluate current techniques by using the experiments and suggest their improvements. The translation systems in this thesis used the neural network transformer architecture and were trained by the Marian framework. The selected language pairs were Slovak with Croatian and Slovak with Serbian. The subjects of the experiments were the transfer learning techniques and semi-supervised learning.
|
|
|
Dictionary of Croatian-Belarussian interlingual homonyms
Bialkovich, Veranika ; Nábělková, Mira (advisor) ; Jirásek, Karel (referee)
The thesis deals with interlingual lexical homonymy in the Croatian and Belarusian languages. The core of the thesis is a Croatian-Belarusian dictionary of homonyms. The preceding, theoretical part focuses first on the denomination of the linguistic phenomenon of interlingual homonymy and on the existing research in the sphere of homonymy among the Slavic languages. A following section of the thesis is devoted to the various types of intralingual and interlingual homonyms and to some differences in their classification. The thesis also looks at the ways in which interlingual homonyms originate, in relation to the origin of the lexical units that make pairs of homonyms. Two principal ways in which pairs of homonyms can originate are described: coincidental formal agreement and agreement as a result of common development or of the borrowing of the same foreign word. Depending on their origin, homonyms are divided into pairs representing the common Slavic lexical stock and pairs of foreign origin. The next part of the thesis presents the principles under which lexicographic material for the dictionary was collected, the lexicographic sources used in the process, and the structure of the dictionary entries. The dictionary of Croatian-Belarusian interlingual homonyms contains 1,048 entries, which represent all...
|
|
|
Dictionary of Croatian-Belarussian interlingual homonyms
Bialkovich, Veranika ; Nábělková, Mira (advisor) ; Jirásek, Karel (referee)
The thesis deals with interlingual lexical homonymy in the Croatian and Belarusian languages. The core of the thesis is a Croatian-Belarusian dictionary of homonyms. The preceding, theoretical part focuses first on the denomination of the linguistic phenomenon of interlingual homonymy and on the existing research in the sphere of homonymy among the Slavic languages. A following section of the thesis is devoted to the various types of intralingual and interlingual homonyms and to some differences in their classification. The thesis also looks at the ways in which interlingual homonyms originate, in relation to the origin of the lexical units that make pairs of homonyms. Two principal ways in which pairs of homonyms can originate are described: coincidental formal agreement and agreement as a result of common development or of the borrowing of the same foreign word. Depending on their origin, homonyms are divided into pairs representing the common Slavic lexical stock and pairs of foreign origin. The next part of the thesis presents the principles under which lexicographic material for the dictionary was collected, the lexicographic sources used in the process, and the structure of the dictionary entries. The dictionary of Croatian-Belarusian interlingual homonyms contains 1,048 entries, which represent all...
|
|
|
Low-Resource Neural Machine Translation
Filo, Denis ; Fajčík, Martin (referee) ; Jon, Josef (advisor)
This thesis deals with neural machine translation (NMT) for low-resource languages. The goal was to evaluate current techniques by using the experiments and suggest their improvements. The translation systems in this thesis used the neural network transformer architecture and were trained by the Marian framework. The selected language pairs were Slovak with Croatian and Slovak with Serbian. The subjects of the experiments were the transfer learning techniques and semi-supervised learning.
|
|
|
A Comparative Index of the Dictionaries Produced under the Commission for Old Church Slavonic Lexicology and Lexicography
Ribarova, Zdenka
The Comparative Index represents the entire lexicographic corpus found in Dictionaries of Old Slavonic and Old Church Slavonic language produced under the Commission for Old Church Slavonic Lexicology and Lexicography. In all these dictionaries the modern approach used in contemporary paleoslavistic lexicography is applied, which enables their comparison. This comparative view provides us with information about the lexis specificity in each Dictionary and its contribution in the light of the evolution of Old Church Slavonic. This Index provides the most exhaustive and thorough register of the Old Slavonic and Old Church Slavonic lexicographic corpus as it is, and also opens up many possibilities for further research and enriching it with new data.
|
|
|
Dictionary of Croatian-Belarussian interlingual homonyms
Bialkovich, Veranika ; Nábělková, Mira (advisor) ; Jirásek, Karel (referee)
The thesis deals with interlingual lexical homonymy in the Croatian and Belarusian languages. The core of the thesis is a Croatian-Belarusian dictionary of homonyms. The preceding, theoretical part focuses first on the denomination of the linguistic phenomenon of interlingual homonymy and on the existing research in the sphere of homonymy among the Slavic languages. A following section of the thesis is devoted to the various types of intralingual and interlingual homonyms and to some differences in their classification. The thesis also looks at the ways in which interlingual homonyms originate, in relation to the origin of the lexical units that make pairs of homonyms. Two principal ways in which pairs of homonyms can originate are described: coincidental formal agreement and agreement as a result of common development or of the borrowing of the same foreign word. Depending on their origin, homonyms are divided into pairs representing the common Slavic lexical stock and pairs of foreign origin. The next part of the thesis presents the principles under which lexicographic material for the dictionary was collected, the lexicographic sources used in the process, and the structure of the dictionary entries. The dictionary of Croatian-Belarusian interlingual homonyms contains 1,048 entries, which represent all...
|
|
|
Dictionary of Croatian-Belarussian interlingual homonyms
Bialkovich, Veranika ; Nábělková, Mira (advisor) ; Jirásek, Karel (referee)
The thesis deals with interlingual lexical homonymy in the Croatian and Belarusian languages. The core of the thesis is a Croatian-Belarusian dictionary of homonyms. The preceding, theoretical part focuses first on the denomination of the linguistic phenomenon of interlingual homonymy and on the existing research in the sphere of homonymy among the Slavic languages. A following section of the thesis is devoted to the various types of intralingual and interlingual homonyms and to some differences in their classification. The thesis also looks at the ways in which interlingual homonyms originate, in relation to the origin of the lexical units that make pairs of homonyms. Two principal ways in which pairs of homonyms can originate are described: coincidental formal agreement and agreement as a result of common development or of the borrowing of the same foreign word. Depending on their origin, homonyms are divided into pairs representing the common Slavic lexical stock and pairs of foreign origin. The next part of the thesis presents the principles under which lexicographic material for the dictionary was collected, the lexicographic sources used in the process, and the structure of the dictionary entries. The dictionary of Croatian-Belarusian interlingual homonyms contains 1,048 entries, which represent all...
|
|
|
Speech Recognition For Selected Languages
Schmitt, Jan ; Karafiát, Martin (referee) ; Janda, Miloš (advisor)
This bachelor's thesis deals with recognition of continues speech for three languages - Bulgarian, Croatian and Swedish. There are described basics of speech processing and recognition methods like acoustic modeling using hidden Markov models and gaussian mixture models. Another aim of this work is preparing data for those languages from GlobalPhone database, so they may be used with speech recognition toolkits Kaldi and HTK. With data prepared there are several models trained and tested using Kaldi toolkit.
|
guest ::
