Automatic language identification using long short-term memory recurrent neural networks

By Javier Gonzalez-Dominguez, Ignacio Lopez-Moreno, Hasim Sak, Joaquin Gonzalez-Rodriguez, Pedro J. Moreno Mengibar. 2014

164 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “LSTM-based systems also set benchmark records in language identification (Gonzalez-Dominguez et al., 2014), medium-vocabulary speech recognition (Geiger et al.”
RUDDER: Return Decomposition for Delayed Rewards (2018, background): “LSTM networks have been overwhelming successful in different speech and language applications, including handwriting recognition [37], generation of writings [38], language modeling and identification [35, 146], automatic language translation [126], speech recognition [107, 29] analysis of audio dat”
Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System (2018, background): “In recent years, with the merit of large labeled datasets, enormous computation capability, and effective network architectures, emerging progress towards end-to-end learning opens up a new area for exploration [19, 20, 21, 22, 23].”
End-to-end text-dependent speaker verification (2015, background): “To the best of our knowledge, recurrent neural networks have been applied to related problems such as speaker identification [16] and language identification [17], but not to the speaker verification task.”
LID-Senones and Their Statistics for Language Identification (2018, background): “[17] also presented end-to-end schemes that performed”
Explaining and Interpreting LSTMs (2019, background): “LSTM networks have been overwhelmingly successful in different speech and language applications, including handwriting recognition [24], generation of writings [23], language modeling and identification [22,78], automatic language translation [73], speech recognition [63,17], analysis of audio data ”
A Novel Learnable Dictionary Encoding Layer for End-to-End Language Identification (2018, background): “In order to feed into the network, as is done in [13, 14, 15, 16], the original input feature sequence has to be resized or cropped into multiple small fixed-size segments in frame level.”
Spoken Language Recognition using X-vectors (2018, background): “In language recognition, a popular approach is to train the neural network to classify languages at the framelevel [7, 8, 9, 10].”
End-to-End Language Identification Using Attention-Based Recurrent Neural Networks (2016, methodology): “Further, LSTM RNN [13, 14] is adopted to the LID task to model the long-range dependency across the input temporal sequence with respect to feed forward neural networks [12, 15].”
A Divide-and-Conquer Approach for Language Identification Based on Recurrent Neural Networks (2016, methodology): “For spoken language identification, [14] showed that LSTM-RNN can outperform other LID techniques on short utterances for a small number (8) of languages.”
Modeling speaker variability using long short-term memory networks for speech recognition (2015, methodology): “Especially, in LID, the LSTM RNN based systems were compared with i-vector and DNN based systems, and shown better performance [21].”
Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition (2014, methodology): “For language identification , LSTM based approach was proposed in [13] to compared with i-vecto r and DNN systems, and better performance was achieved.”