Kazakh and Russian languages identification using long short-term memory recurrent neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Automatic language identification (LID) belongs to the automatic process whereby the identity of the language spoken in a speech sample can be distinguished. In recent decades, LID has made significant advancement in spoken language identification which received an advantage from technological achievements in related areas, such as signal processing, pattern recognition, machine learning and neural networks. This work investigates the employment of Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) for automatic language identification. The main reason of applying LSTM RNNs to the current task is their reasonable capacity in handling sequences. This study shows that LSTM RNNs can efficiently take advantage of temporal dependencies in acoustic data in order to learn relevant features for language recognition tasks. In this paper, we show results for conducted language identification experiments for Kazakh and Russian languages and the presented LSTM RNN model can deal with short utterances (2s). The model was trained using open-source high-level neural networks API Keras on limited computational resources.

Original languageEnglish
Title of host publication11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538605011
DOIs
Publication statusPublished - Apr 10 2019
Event11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Moscow, Russian Federation
Duration: Sep 20 2017Sep 22 2017

Publication series

Name11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings

Conference

Conference11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017
CountryRussian Federation
CityMoscow
Period9/20/179/22/17

Fingerprint

Recurrent neural networks
Neural networks
Application programming interfaces (API)
Pattern recognition
Learning systems
Signal processing
Acoustics
Long short-term memory
Experiments

Keywords

  • Language identification
  • Long Short-Term Memory Recurrent Neural Networks

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Kozhirbayev, Z., Yessenbayev, Z., & Karabalayeva, M. (2019). Kazakh and Russian languages identification using long short-term memory recurrent neural networks. In 11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings [8687095] (11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAICT.2017.8687095

Kazakh and Russian languages identification using long short-term memory recurrent neural networks. / Kozhirbayev, Zhanibek; Yessenbayev, Zhandos; Karabalayeva, Muslima.

11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8687095 (11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kozhirbayev, Z, Yessenbayev, Z & Karabalayeva, M 2019, Kazakh and Russian languages identification using long short-term memory recurrent neural networks. in 11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings., 8687095, 11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017, Moscow, Russian Federation, 9/20/17. https://doi.org/10.1109/ICAICT.2017.8687095
Kozhirbayev Z, Yessenbayev Z, Karabalayeva M. Kazakh and Russian languages identification using long short-term memory recurrent neural networks. In 11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8687095. (11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings). https://doi.org/10.1109/ICAICT.2017.8687095
Kozhirbayev, Zhanibek ; Yessenbayev, Zhandos ; Karabalayeva, Muslima. / Kazakh and Russian languages identification using long short-term memory recurrent neural networks. 11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings).
@inproceedings{7dcaa212094549aeb63e3c63d9e4e113,
title = "Kazakh and Russian languages identification using long short-term memory recurrent neural networks",
abstract = "Automatic language identification (LID) belongs to the automatic process whereby the identity of the language spoken in a speech sample can be distinguished. In recent decades, LID has made significant advancement in spoken language identification which received an advantage from technological achievements in related areas, such as signal processing, pattern recognition, machine learning and neural networks. This work investigates the employment of Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) for automatic language identification. The main reason of applying LSTM RNNs to the current task is their reasonable capacity in handling sequences. This study shows that LSTM RNNs can efficiently take advantage of temporal dependencies in acoustic data in order to learn relevant features for language recognition tasks. In this paper, we show results for conducted language identification experiments for Kazakh and Russian languages and the presented LSTM RNN model can deal with short utterances (2s). The model was trained using open-source high-level neural networks API Keras on limited computational resources.",
keywords = "Language identification, Long Short-Term Memory Recurrent Neural Networks",
author = "Zhanibek Kozhirbayev and Zhandos Yessenbayev and Muslima Karabalayeva",
year = "2019",
month = "4",
day = "10",
doi = "10.1109/ICAICT.2017.8687095",
language = "English",
series = "11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings",
address = "United States",

}

TY - GEN

T1 - Kazakh and Russian languages identification using long short-term memory recurrent neural networks

AU - Kozhirbayev, Zhanibek

AU - Yessenbayev, Zhandos

AU - Karabalayeva, Muslima

PY - 2019/4/10

Y1 - 2019/4/10

N2 - Automatic language identification (LID) belongs to the automatic process whereby the identity of the language spoken in a speech sample can be distinguished. In recent decades, LID has made significant advancement in spoken language identification which received an advantage from technological achievements in related areas, such as signal processing, pattern recognition, machine learning and neural networks. This work investigates the employment of Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) for automatic language identification. The main reason of applying LSTM RNNs to the current task is their reasonable capacity in handling sequences. This study shows that LSTM RNNs can efficiently take advantage of temporal dependencies in acoustic data in order to learn relevant features for language recognition tasks. In this paper, we show results for conducted language identification experiments for Kazakh and Russian languages and the presented LSTM RNN model can deal with short utterances (2s). The model was trained using open-source high-level neural networks API Keras on limited computational resources.

AB - Automatic language identification (LID) belongs to the automatic process whereby the identity of the language spoken in a speech sample can be distinguished. In recent decades, LID has made significant advancement in spoken language identification which received an advantage from technological achievements in related areas, such as signal processing, pattern recognition, machine learning and neural networks. This work investigates the employment of Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) for automatic language identification. The main reason of applying LSTM RNNs to the current task is their reasonable capacity in handling sequences. This study shows that LSTM RNNs can efficiently take advantage of temporal dependencies in acoustic data in order to learn relevant features for language recognition tasks. In this paper, we show results for conducted language identification experiments for Kazakh and Russian languages and the presented LSTM RNN model can deal with short utterances (2s). The model was trained using open-source high-level neural networks API Keras on limited computational resources.

KW - Language identification

KW - Long Short-Term Memory Recurrent Neural Networks

UR - http://www.scopus.com/inward/record.url?scp=85052065195&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052065195&partnerID=8YFLogxK

U2 - 10.1109/ICAICT.2017.8687095

DO - 10.1109/ICAICT.2017.8687095

M3 - Conference contribution

AN - SCOPUS:85052065195

T3 - 11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings

BT - 11th IEEE International Conference on Application of Information and Communication Technologies, AICT 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -