Browse Subject Areas

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Language Identification in Short Utterances Using Long Short-Term Memory (LSTM) Recurrent Neural Networks

Fig 1

DNN network topology.

In this paper we use one or two hidden layers replacing each hidden unit with an uni-directional LSTM memory block with forget gates and peepholes.

Fig 1