KALAKA-3 Database Language Classifier Through Convolutional Recurrent Neural Network

Jorge O. Ordoñez Ordoñez; Luis F. Guerrero Vasquez; Paul A. Chasi-Pesantez; David P. Barros-Piedra; Edwin J. Coronel González

doi:10.1007/978-981-99-3043-2_51

KALAKA-3 Database Language Classifier Through Convolutional Recurrent Neural Network

Jorge O. Ordoñez Ordoñez, Luis F. Guerrero Vasquez, Paul A. Chasi-Pesantez, David P. Barros-Piedra, Edwin J. Coronel González

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

During the last few years, the field of automatic speech recognition (ASR) has been growing exponentially, due to the diverse applications and solutions it offers. For this reason, this paper presents a multiclass language classifier based on recurrent convolutional neural networks, whose objective is to classify the audios of the KALAKA-3 database, according to their language. To meet this objective, the mel frequency cepstral coefficients (MFCCs) were extracted from each of the audios in the database, with which the training process is carried out. A recurrent convolutional neural network (CRNN) was created for this process, resulting in an accuracy of 98% using the testing data, and 40% using the Eval data. This work sets a precedent for improving real-time translators, since in the future it would be possible to listen to a few seconds of a conversation, identify it, and automatically perform a translation process, which would be very useful in various applications.

Original language	English
Title of host publication	Proceedings of 8th International Congress on Information and Communication Technology - ICICT 2023
Editors	Xin-She Yang, R. Simon Sherratt, Nilanjan Dey, Amit Joshi
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	641-649
Number of pages	9
ISBN (Print)	9789819930425
DOIs	https://doi.org/10.1007/978-981-99-3043-2_51
State	Published - 2024
Event	8th International Congress on Information and Communication Technology, ICICT 2023 - London, United Kingdom Duration: 20 Feb 2023 → 23 Feb 2023

Publication series

Name	Lecture Notes in Networks and Systems
Volume	695 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	8th International Congress on Information and Communication Technology, ICICT 2023
Country/Territory	United Kingdom
City	London
Period	20/02/23 → 23/02/23

Bibliographical note

Publisher Copyright:
© 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Keywords

Artificial intelligence
CRNN
Database
KALAKA-3
Neural networks

Access to Document

10.1007/978-981-99-3043-2_51

Cite this

Ordoñez Ordoñez, J. O., Guerrero Vasquez, L. F., Chasi-Pesantez, P. A., Barros-Piedra, D. P., & Coronel González, E. J. (2024). KALAKA-3 Database Language Classifier Through Convolutional Recurrent Neural Network. In X.-S. Yang, R. S. Sherratt, N. Dey, & A. Joshi (Eds.), Proceedings of 8th International Congress on Information and Communication Technology - ICICT 2023 (pp. 641-649). (Lecture Notes in Networks and Systems; Vol. 695 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-3043-2_51

Ordoñez Ordoñez, Jorge O. ; Guerrero Vasquez, Luis F. ; Chasi-Pesantez, Paul A. et al. / KALAKA-3 Database Language Classifier Through Convolutional Recurrent Neural Network. Proceedings of 8th International Congress on Information and Communication Technology - ICICT 2023. editor / Xin-She Yang ; R. Simon Sherratt ; Nilanjan Dey ; Amit Joshi. Springer Science and Business Media Deutschland GmbH, 2024. pp. 641-649 (Lecture Notes in Networks and Systems).

@inproceedings{e8427e21d51746b6b900f406b8dde6d6,

title = "KALAKA-3 Database Language Classifier Through Convolutional Recurrent Neural Network",

abstract = "During the last few years, the field of automatic speech recognition (ASR) has been growing exponentially, due to the diverse applications and solutions it offers. For this reason, this paper presents a multiclass language classifier based on recurrent convolutional neural networks, whose objective is to classify the audios of the KALAKA-3 database, according to their language. To meet this objective, the mel frequency cepstral coefficients (MFCCs) were extracted from each of the audios in the database, with which the training process is carried out. A recurrent convolutional neural network (CRNN) was created for this process, resulting in an accuracy of 98% using the testing data, and 40% using the Eval data. This work sets a precedent for improving real-time translators, since in the future it would be possible to listen to a few seconds of a conversation, identify it, and automatically perform a translation process, which would be very useful in various applications.",

keywords = "Artificial intelligence, CRNN, Database, KALAKA-3, Neural networks",

author = "{Ordo{\~n}ez Ordo{\~n}ez}, {Jorge O.} and {Guerrero Vasquez}, {Luis F.} and Chasi-Pesantez, {Paul A.} and Barros-Piedra, {David P.} and {Coronel Gonz{\'a}lez}, {Edwin J.}",

note = "Publisher Copyright: {\textcopyright} 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 8th International Congress on Information and Communication Technology, ICICT 2023 ; Conference date: 20-02-2023 Through 23-02-2023",

year = "2024",

doi = "10.1007/978-981-99-3043-2_51",

language = "English",

isbn = "9789819930425",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "641--649",

editor = "Xin-She Yang and Sherratt, {R. Simon} and Nilanjan Dey and Amit Joshi",

booktitle = "Proceedings of 8th International Congress on Information and Communication Technology - ICICT 2023",

address = "Germany",

}

Ordoñez Ordoñez, JO , Guerrero Vasquez, LF , Chasi-Pesantez, PA, Barros-Piedra, DP & Coronel González, EJ 2024, KALAKA-3 Database Language Classifier Through Convolutional Recurrent Neural Network. in X-S Yang, RS Sherratt, N Dey & A Joshi (eds), Proceedings of 8th International Congress on Information and Communication Technology - ICICT 2023. Lecture Notes in Networks and Systems, vol. 695 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 641-649, 8th International Congress on Information and Communication Technology, ICICT 2023, London, United Kingdom, 20/02/23. https://doi.org/10.1007/978-981-99-3043-2_51

KALAKA-3 Database Language Classifier Through Convolutional Recurrent Neural Network. / Ordoñez Ordoñez, Jorge O.; Guerrero Vasquez, Luis F.; Chasi-Pesantez, Paul A. et al.
Proceedings of 8th International Congress on Information and Communication Technology - ICICT 2023. ed. / Xin-She Yang; R. Simon Sherratt; Nilanjan Dey; Amit Joshi. Springer Science and Business Media Deutschland GmbH, 2024. p. 641-649 (Lecture Notes in Networks and Systems; Vol. 695 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - KALAKA-3 Database Language Classifier Through Convolutional Recurrent Neural Network

AU - Ordoñez Ordoñez, Jorge O.

AU - Guerrero Vasquez, Luis F.

AU - Chasi-Pesantez, Paul A.

AU - Barros-Piedra, David P.

AU - Coronel González, Edwin J.

PY - 2024

Y1 - 2024

N2 - During the last few years, the field of automatic speech recognition (ASR) has been growing exponentially, due to the diverse applications and solutions it offers. For this reason, this paper presents a multiclass language classifier based on recurrent convolutional neural networks, whose objective is to classify the audios of the KALAKA-3 database, according to their language. To meet this objective, the mel frequency cepstral coefficients (MFCCs) were extracted from each of the audios in the database, with which the training process is carried out. A recurrent convolutional neural network (CRNN) was created for this process, resulting in an accuracy of 98% using the testing data, and 40% using the Eval data. This work sets a precedent for improving real-time translators, since in the future it would be possible to listen to a few seconds of a conversation, identify it, and automatically perform a translation process, which would be very useful in various applications.

AB - During the last few years, the field of automatic speech recognition (ASR) has been growing exponentially, due to the diverse applications and solutions it offers. For this reason, this paper presents a multiclass language classifier based on recurrent convolutional neural networks, whose objective is to classify the audios of the KALAKA-3 database, according to their language. To meet this objective, the mel frequency cepstral coefficients (MFCCs) were extracted from each of the audios in the database, with which the training process is carried out. A recurrent convolutional neural network (CRNN) was created for this process, resulting in an accuracy of 98% using the testing data, and 40% using the Eval data. This work sets a precedent for improving real-time translators, since in the future it would be possible to listen to a few seconds of a conversation, identify it, and automatically perform a translation process, which would be very useful in various applications.

KW - Artificial intelligence

KW - CRNN

KW - Database

KW - KALAKA-3

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=85174723935&partnerID=8YFLogxK

U2 - 10.1007/978-981-99-3043-2_51

DO - 10.1007/978-981-99-3043-2_51

M3 - Conference contribution

AN - SCOPUS:85174723935

SN - 9789819930425

T3 - Lecture Notes in Networks and Systems

SP - 641

EP - 649

BT - Proceedings of 8th International Congress on Information and Communication Technology - ICICT 2023

A2 - Yang, Xin-She

A2 - Sherratt, R. Simon

A2 - Dey, Nilanjan

A2 - Joshi, Amit

PB - Springer Science and Business Media Deutschland GmbH

T2 - 8th International Congress on Information and Communication Technology, ICICT 2023

Y2 - 20 February 2023 through 23 February 2023

ER -

Ordoñez Ordoñez JO , Guerrero Vasquez LF , Chasi-Pesantez PA, Barros-Piedra DP, Coronel González EJ. KALAKA-3 Database Language Classifier Through Convolutional Recurrent Neural Network. In Yang XS, Sherratt RS, Dey N, Joshi A, editors, Proceedings of 8th International Congress on Information and Communication Technology - ICICT 2023. Springer Science and Business Media Deutschland GmbH. 2024. p. 641-649. (Lecture Notes in Networks and Systems). doi: 10.1007/978-981-99-3043-2_51

KALAKA-3 Database Language Classifier Through Convolutional Recurrent Neural Network

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this