Language Identification in Short Utterances Using Long Short-Term Memory (LSTM) Recurrent Neural Networks.
Long Short Term Memory (LSTM) Recurrent Neural Networks (RNNs) have recently outperformed other state-of-the-art approaches, such as i-vector and Deep Neural Networks (DNNs), in automatic Language Identification (LID), particularly when dealing with very short utterances (∼3s). In this contribution...
Main Authors: | Ruben Zazo, Alicia Lozano-Diez, Javier Gonzalez-Dominguez, Doroteo T Toledano, Joaquin Gonzalez-Rodriguez |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2016-01-01
|
Series: | PLoS ONE |
Online Access: | http://europepmc.org/articles/PMC4732772?pdf=render |
Similar Items
-
Age Estimation in Short Speech Utterances Based on LSTM Recurrent Neural Networks
by: Ruben Zazo, et al.
Published: (2018-01-01) -
An analysis of the influence of deep neural network (DNN) topology in bottleneck feature based language recognition.
by: Alicia Lozano-Diez, et al.
Published: (2017-01-01) -
Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset
by: Diego de Benito-Gorron, et al.
Published: (2019-06-01) -
Native Language Identification in Very Short Utterances Using Bidirectional Long Short-Term Memory Network
by: Farah Adeeba, et al.
Published: (2019-01-01) -
Using a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) to Classify Network Attacks
by: Pramita Sree Muhuri, et al.
Published: (2020-05-01)