Return to search

Rekurentní neuronové sítě pro rozpoznávání řeči / Recurrent Neural Networks for Speech Recognition

This master thesis deals with the implementation of various types of recurrent neural networks via programming language lua using torch library. It focuses on finding optimal strategy for training recurrent neural networks and also tries to minimize the duration of the training. Furthermore various types of regularization techniques are investigated and implemented into the recurrent neural network architecture. Implemented recurrent neural networks are compared on the speech recognition task using AMI dataset, where they model the acustic information. Their performance is also compared to standard feedforward neural network. Best results are achieved using BLSTM architecture. The recurrent neural network are also trained via CTC objective function on the TIMIT dataset. Best result is again achieved using BLSTM architecture.

Identiferoai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:255371
Date January 2016
CreatorsNováčik, Tomáš
ContributorsKarafiát, Martin, Veselý, Karel
PublisherVysoké učení technické v Brně. Fakulta informačních technologií
Source SetsCzech ETDs
LanguageCzech
Detected LanguageEnglish
Typeinfo:eu-repo/semantics/masterThesis
Rightsinfo:eu-repo/semantics/restrictedAccess

Page generated in 0.0016 seconds