| dc.contributor.author | Shewalkar, Apeksha Nagesh | |
| dc.description.abstract | Deep 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. | en_US |
| dc.publisher | North Dakota State University | en_US |
| dc.rights | NDSU Policy 190.6.2 | |
| dc.title | Comparison of RNN, LSTM and GRU on Speech Recognition Data | en_US |
| dc.type | Master's paper | en_US |
| dc.date.accessioned | 2018-12-18T21:33:24Z | |
| dc.date.available | 2018-12-18T21:33:24Z | |
| dc.date.issued | 2018 | |
| dc.identifier.uri | https://hdl.handle.net/10365/29111 | |
| dc.subject | Recurrent neural networks. | en_US |
| dc.subject | Long short-term memory networks. | en_US |
| dc.subject | Gated recurrent unit networks. | en_US |
| dc.subject | Speech recognition. | en_US |
| dc.subject | Deep learning. | en_US |
| dc.subject | Deep neural networks. | en_US |
| dc.subject | TED-LIUM speech data. | en_US |
| dc.subject.lcsh | Neural networks (Computer science) | |
| dc.subject.lcsh | Machine learning. | |
| dc.subject.lcsh | Automatic speech recognition. | |
| dc.subject.lcsh | Natural language processing (Computer science) | en_US |
| dc.rights.uri | https://www.ndsu.edu/fileadmin/policy/190.pdf | |
| ndsu.degree | Master of Science (MS) | en_US |
| ndsu.college | Engineering | en_US |
| ndsu.department | Computer Science | en_US |
| ndsu.program | Computer Science | en_US |
| ndsu.advisor | Ludwig, Simone | |
