Thesis Details
Doplňování interpunkce do automatického přepisu řeči
This thesis deals with the problem of punctuation reconstruction in the output of automatic speech recognition systems. Constrains given on the solutions were applicability on general spoken English language and reasonable accuracy of the punctuation prediction system. Natural language tends to have in some cases non-deterministic nature and usually consists of a large number of grammatic rules. Therefore, a machine learning approach was chosen to solve this problem for its ability to recognize complicated patterns in data. A number of experiments with recurrent neural networks were executed to find the best network architecture for punctuation prediction. Resulting models created during these experiments reach accuracy comparable if not better than the works currently held as state-of-the-art solutions for punctuation reconstruction.
natural language processing, recurrent neural networks, machine learning
Bidlo Michal, doc. Ing., Ph.D. (DCSY FIT BUT), člen
Hliněná Dana, doc. RNDr., Ph.D. (DMAT FEEC BUT), člen
Rozman Jaroslav, Ing., Ph.D. (DITS FIT BUT), člen
Ryšavý Ondřej, doc. Ing., Ph.D. (DIFS FIT BUT), člen
@bachelorsthesis{FITBT19557, author = "Tom\'{a}\v{s} \v{S}\v{c}avnick\'{y}", type = "Bachelor's thesis", title = "Dopl\v{n}ov\'{a}n\'{i} interpunkce do automatick\'{e}ho p\v{r}episu \v{r}e\v{c}i", school = "Brno University of Technology, Faculty of Information Technology", year = 2017, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/19557/" }