|
| |
|
| |
|
|
Automatic Creation of Organ Overtures for Church Songs
Maňák, Ondřej ; Černocký, Jan (referee) ; Fapšo, Michal (advisor)
The focus of this master's thesis is an automatic creation of organ overtures for church songs from both theoretical and practical points of view. Organ overture is a short introduction to a church song. According to the fact that it can be described by a finite set of rules, it is possible to use techniques for solving Constraint Satisfaction Problems. An effective instrument to develop such system can be C++ programming language and Gecode library.
|
|
| |
|
|
Language Modeling for Spech Recognition in Czech
Mikolov, Tomáš ; Černocký, Jan (referee) ; Smrž, Pavel (advisor)
This work concerns the problematic of language modeling in automatic speech recognition. Currently widely used techniques for advanced language modeling based on statistical approach are described in the first part of work - class based language models, factored language models and neural network based language models. In the next section, implementation of neural network based language model is described. Results obtained on "Pražský mluvený korpus" and "Brněnský mluvený korpus" corpora (1 170 000 words) are reported, with perplexity reduction around 20%. Also, results obtained after rescoring N-best lists with spontaneous speech are reported, with absolute improvement in accuracy by more than 1%. In the conclusion, possible uses of the work are mentioned, along with possible extensions in the future. Finally, main weaknesses of current statistical language modeling techniques are described.
|
|
|
Modelling Emotions in Communication Agents
Sivák, Martin ; Černocký, Jan (referee) ; Smrž, Pavel (advisor)
This work deals with current chatterbot systems. It describes problems and possibilities of improvement with emphasis on natural language processing and emotion modeling during conversation. There is an implementation, based on the described knowledge, introduced in the second part of the thesis, also with experimental success rate evaluation.
|
|
|
Searching in Speech Data
Fapšo, Michal ; Černocký, Jan (referee) ; Szőke, Igor (advisor)
This thesis describes a designed and implemented system for efficient storage, indexing and search in collections of spoken documents that takes advantage of automatic speech recognition. As the quality of current speech recognizers is not sufficient for a great deal of applications, it is necessary to index the ambiguous output of the recognition, i.\,e. the acyclic graphs of word hypotheses -- recognition lattices. Then, it is not possible to directly apply the standard methods known from text--based systems. This paper discusses an optimized indexing system for efficient search in the complex and large data structures which are the output of the recognizer.
|
|
|
Search in Music Signals
Skála, František ; Szőke, Igor (referee) ; Černocký, Jan (advisor)
This work contains overview of methods used in the area of Music Information Retrieval, mainly for purposes of searching of musical recordings. Several existing services in the areas of music identification and searching are presented and their methods for unique song identification are described. This work also focuses on possible modifications of these algorithms for searching of cover versions of songs and for the possibility of searching based on voice created examples.
|
|
| |
|
|
Speaker Recognition Based on Long Temporal Context
Fér, Radek ; Matějka, Pavel (referee) ; Černocký, Jan (advisor)
Tato práce se zabývá extrakcí vhodných příznaků pro rozpoznávání řečníka z delších časových úseků. Po představení současných technik pro extrakci takových příznaků navrhujeme a popisujeme novou metodu pracující v časovém rozsahu fonémů a využívající známou techniku i-vektorů. Velké úsilí bylo vynaloženo na nalezení vhodné reprezentace temporálních příznaků, díky kterým by mohly být systémy pro rozpoznávání řečníka robustnější, zejména modelování prosodie. Náš přístup nemodeluje explicitně žádné specifické temporální parametry řeči, namísto toho používá kookurenci řečových rámců jako zdroj temporálních příznaků. Tuto techniku testujeme a analyzujeme na řečové databázi NIST SRE 2008. Z výsledků bohužel vyplývá, že pro rozpoznávání řečníka tato technika nepřináší očekávané zlepšení. Tento fakt diskutujeme a analyzujeme ke konci práce.
|
guest ::
