|
|
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.
|
|
|
Simple Czech Grammar Correcttor for OpenOffice
Ličko, Jozef ; Herout, Adam (referee) ; Smrž, Pavel (advisor)
The grammar of natural language is generally complex. Often, it is very difficult to describe it precisely in a formal way. There are several approaches to grammar correction using computer technologies. This thesis deals with the construction of a simple rule-based Czech grammar checker. It focuses on subordinate relative constructions. The corrector is designed to identify missing comma in them. If such a sentence is found the program proposes possible suggestions how to correct it. The application operates as a plugin for OpenOffice suite.
|
|
| |
|
|
Machine Learning for Natural Language Question Answering
Sasín, Jonáš ; Fajčík, Martin (referee) ; Smrž, Pavel (advisor)
This thesis deals with natural language question answering using Czech Wikipedia. Question answering systems are experiencing growing popularity, but most of them are developed for English. The main purpose of this work is to explore possibilities and datasets available and create such system for Czech. In the thesis I focused on two approaches. One of them uses English model ALBERT and machine translation of passages. The other one utilizes the multilingual BERT. Several variants of the system are compared in this work. Possibilities of relevant passage retrieval are also discussed. Standard evaluation is provided for every variant of the tested system. The best system version has been evaluated on the SQAD v3.0 dataset, reaching 0.44 EM and 0.55 F1 score, which is an excellent result compared to other existing systems. The main contribution of this work is the analysis of existing possibilities and setting a benchmark for further development of better systems for Czech.
|
|
|
Encyclopedia Expert
Krč, Martin ; Schmidt, Marek (referee) ; Smrž, Pavel (advisor)
This project focuses on a system that answers questions formulated in natural language. Firstly, the report discusses problems associated with question answering systems and some commonly employed approaches. Emphasis is laid on shallow methods, which do not require many linguistic resources. The second part describes our work on a system that answers factoid questions, utilizing Czech Wikipedia as a source of information. Answer extraction is partly based on specific features of Wikipedia and partly on pre-defined patterns. Results show that for answering simple questions, the system provides significant improvements in comparison with a standard search engine.
|
|
|
Commented Translation: Measurements in Electrotechnics and Audiotechnics
Šustrová, Pavlína ; Krhutová, Milena (referee) ; Kotásek, Miroslav (advisor)
Předmětem této práce je komentovaný překlad instruktá- žního textu používaného v univerzitních kurzech Měření v elektrotechnice a Měření v audiotechnice. Překlad byl vytvořen pro potřeby budoucích zahraničních studentů navštěvujících uvedené kurzy. Komentář uvádí důvody motivace k provedení překladu, překladatelské teorie a pohledy aplikované během překladu, potíže ke kterým v průběhu došlo a jejich individuální řešení, včetně konkrétních příkladů, a stručnou lingvistickou analýzu textu. Kromě samotného překladu tato práce představuje koncept slovníčků které by doprovázely každý laboratorní návod v textu. Finální verze překladu je připravena k posouzení, zda může být použita jako oficiální studijní materiál.
|
|
|
Identification of emotional state using speech signal analysis
Navrátil, Michal ; Atassi, Hicham (referee) ; Smékal, Zdeněk (advisor)
The diploma thesis deals with the analysis of human emotional states speaker by the help of analyse speech signals. The thesis has two parts. In the first part, the process of speech generating is described in addition to the description of the commonly used pre-processing methods such as denoising or preemphasis. The first part also deals with the major and minor prosody features, these features are: the fundamental frequency, energy, spectral features and time domain features such as the speech rate. The second part of this thesis deals with a task of emotion recognition from the speech signal. When we accumulate sufficient of the number of recordings emotive state will be able to rekognize emotive state with high probability. All project is prepared for use in real time. The last part of this thesis thesis contains description and results of the experiments made on a large number of speech records.
|
|
| |
|
|
The Interpretation Process betwen Czech and Portuguese Language: an Approach Towards Selected Linguistic Problems
Hrušovská, Petra ; Jindrová, Jaroslava (advisor) ; Hricsina, Jan (referee)
The present thesis, The Interpretation Process between Czech and Portuguese Language: an Approach Towards Selected Linguistic Problems, analyses the two languages belonging to different language families from the interpreter's point of view. The Introduction gives rea- sons for choosing the topic and outlines the general structure of the thesis. Chapter 1 (Lan- guages and Interpreting) delineates theoretical issues pertinent to language typology accord- ing to Skalička, comparing the structures of Czech and Portuguese, and outlines a basic intro- duction to interpreting. The principal subject is defined as selected linguistic problems that intepreters have to deal with when working with Czech and Portuguese. Chapter 2 (Transla- tion Procedures) focuses on methods and procedures of translation, in particular those pro- posed by Vinay and Darbelnet. Chapter 3 (Morphology and Syntax) gives a contrastive analy- sis with sample translations of substantives, adjectives, pronouns and articles in both lan- guages. The last chapter (lexicology) describes some phenomena related to lexical questions (interferences, synonymy and phraseology). The thesis is concluded by stressing the role of context in interpreting, leading eventually to some limitations for the analysis. Key words: Czech, Portuguese, Typology...
|
|
| |
guest ::
