Thesis Details
Modelování jazyka v rozpoznávání češtiny
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.
language modeling, Czech language, n-gram statistics, neural networks, speech recognition, artificial intelligence
Fučík Otto, doc. Dr. Ing. (DCSY FIT BUT), člen
Křena Bohuslav, Ing., Ph.D. (DITS FIT BUT), člen
Racek Stanislav, doc. Ing., CSc. (WBU in Pilsen), člen
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT), člen
Vojnar Tomáš, prof. Ing., Ph.D. (DITS FIT BUT), člen
@mastersthesis{FITMT3645, author = "Tom\'{a}\v{s} Mikolov", type = "Master's thesis", title = "Modelov\'{a}n\'{i} jazyka v rozpozn\'{a}v\'{a}n\'{i} \v{c}e\v{s}tiny", school = "Brno University of Technology, Faculty of Information Technology", year = 2007, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/3645/" }