Thesis Details
Nové techniky v oblasti trénování neuronových sítí - Connectionist temporal classification
Bachelor's Thesis
Student: Gajdár Matúš
Academic Year: 2016/2017
Supervisor: Karafiát Martin, Ing., Ph.D.
English title
New Techniques in Neural Networks Training - Connectionist Temporal Classification
Language
Czech
Abstract
This bachelor’s thesis deals with neural network and their use in speech recognition. Firstly,there is some theory about speech recognition, afterwards we show theory around neural networks in connection with connectionist temporal classification method. In next chapter we introduce toolkits, which were used for training of neural networks and also experiments done by them to find out impact of connectionist temporal classification method on precisionin phoneme decoding. The last chapter include summarization of work and overall evaluation of experiments.
Keywords
Speech recognition, neural network, CTC, LSTM, CNTK, EESEN
Department
Degree Programme
Information Technology
Files
Status
defended, grade D
Date
16 June 2017
Reviewer
Švec Ján, Ing.
Committee
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT), předseda
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
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
Citation
GAJDÁR, Matúš. Nové techniky v oblasti trénování neuronových sítí - Connectionist temporal classification. Brno, 2017. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2017-06-16. Supervised by Karafiát Martin. Available from: https://www.fit.vut.cz/study/thesis/18499/
BibTeX
@bachelorsthesis{FITBT18499, author = "Mat\'{u}\v{s} Gajd\'{a}r", type = "Bachelor's thesis", title = "Nov\'{e} techniky v oblasti tr\'{e}nov\'{a}n\'{i} neuronov\'{y}ch s\'{i}t\'{i} - Connectionist temporal classification", school = "Brno University of Technology, Faculty of Information Technology", year = 2017, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/18499/" }