Show simple item record

dc.contributor.authorShewalkar, Apeksha Nagesh
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.en_US
dc.publisherNorth Dakota State Universityen_US
dc.rightsNDSU Policy 190.6.2
dc.titleComparison of RNN, LSTM and GRU on Speech Recognition Dataen_US
dc.typeMaster's paperen_US
dc.date.accessioned2018-12-18T21:33:24Z
dc.date.available2018-12-18T21:33:24Z
dc.date.issued2018
dc.identifier.urihttps://hdl.handle.net/10365/29111
dc.subjectRecurrent neural networks.en_US
dc.subjectLong short-term memory networks.en_US
dc.subjectGated recurrent unit networks.en_US
dc.subjectSpeech recognition.en_US
dc.subjectDeep learning.en_US
dc.subjectDeep neural networks.en_US
dc.subjectTED-LIUM speech data.en_US
dc.subject.lcshNeural networks (Computer science)
dc.subject.lcshMachine learning.
dc.subject.lcshAutomatic speech recognition.
dc.subject.lcshNatural language processing (Computer science)en_US
dc.rights.urihttps://www.ndsu.edu/fileadmin/policy/190.pdf
ndsu.degreeMaster of Science (MS)en_US
ndsu.collegeEngineeringen_US
ndsu.departmentComputer Scienceen_US
ndsu.programComputer Scienceen_US
ndsu.advisorLudwig, Simone


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record