|
|
Recurrent Neural Networks for Speech Recognition
Nováčik, Tomáš ; Karafiát, Martin (referee) ; Veselý, Karel (advisor)
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.
|
|
|
Smart Interaction of Robot with Human
Nováčik, Tomáš ; Rozman, Jaroslav (referee) ; Luža, Radim (advisor)
This bachelor thesis investigates the usage of neural networks and their applications on the problem of smart home. Used localization system is based on WLAN technology. For activities rocognition is used LSTM recurrent neural network. For simulation purposes is used robot operating system.
|
|
|
Recurrent Neural Networks for Speech Recognition
Nováčik, Tomáš ; Karafiát, Martin (referee) ; Veselý, Karel (advisor)
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.
|
|
|
Smart Interaction of Robot with Human
Nováčik, Tomáš ; Rozman, Jaroslav (referee) ; Luža, Radim (advisor)
This bachelor thesis investigates the usage of neural networks and their applications on the problem of smart home. Used localization system is based on WLAN technology. For activities rocognition is used LSTM recurrent neural network. For simulation purposes is used robot operating system.
|
guest ::
