Thesis Details
Adaptace jazykového modelu na cílovou doménu využívající stahování veřejných dat
The goal of this thesis is to implement a system for automatic language model adaptation for Phonexia ASR system. System expects input in the form of source that, which is analysed and appropriate terms for web search are chosen. Every web search results in a set of documents that undergo cleaning and filtering procedures. The resulting web corpora is mixed with Phonexia model and evaluated. In order to estimate the most optimal parameters, I conducted 3 sets of experiments for Hindi, Czech and Mandarin. The results of the experiments were very favourable and the implemented system managed to decrease perplexity and Word Error Rate in most cases.
speech-to-text, automatic speech recognition, language model, language model adaptation, automatic web search, automatic web document scraping, automatic assessment of web documents
Hradiš Michal, Ing., Ph.D. (DCGM FIT BUT), člen
Janoušek Vladimír, doc. Ing., Ph.D. (DITS FIT BUT), člen
Kanich Ondřej, Ing., Ph.D. (DITS FIT BUT), člen
Rozman Jaroslav, Ing., Ph.D. (DITS FIT BUT), člen
Zbořil František, doc. Ing., Ph.D. (DITS FIT BUT), člen
@mastersthesis{FITMT24957, author = "Sab\'{i}na Gregu\v{s}ov\'{a}", type = "Master's thesis", title = "Adaptace jazykov\'{e}ho modelu na c\'{i}lovou dom\'{e}nu vyu\v{z}\'{i}vaj\'{i}c\'{i} stahov\'{a}n\'{i} ve\v{r}ejn\'{y}ch dat", school = "Brno University of Technology, Faculty of Information Technology", year = 2022, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/24957/" }