North Dakota State University
Comparison of RNN, LSTM and GRU on Speech Recognition Data
Abstract
dc:description.abstractDeep Learning [DL] provides an efficient way to train Deep Neural Networks [DNN]. DDNs when used for end-to-end Automatic Speech Recognition [ASR] tasks, could produce more accurate results compared to traditional ASR. Normal feedforward neural networks are not suitable for speech data as they cannot persist past information. Whereas Recurrent Neural Networks [RNNs] can persist past information and handle temporal dependencies. For this project, three recurrent networks, standard RNN, Long Short-Term Memory [LSTM] networks and Gated Recurrent Unit [GRU] networks are evaluated in order to compare their performance on speech data. The data set used for the experiments is a reduced version of TED-LIUM speech data. According to the experiments and their evaluation, LSTM performed best among all other networks with a good word error rate at the same time GRU also achieved results close to those of LSTM in less time.
Degree
thesis:*- Grantor dc:publisher
- North Dakota State University
- Year dc:date.issued
- 2018
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Shewalkar, Apeksha Nagesh
Subjects
dc:subject × 11Rights
dc:rights- Statement dc:rights
-
- NDSU Policy 190.6.2
- Licence dc:rights.uri
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/10365/29111