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

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución de conferencia › revisión exhaustiva

Resumen

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.

Idioma original	Inglés
Título de la publicación alojada	Proceedings of 8th International Congress on Information and Communication Technology - ICICT 2023
Editores	Xin-She Yang, R. Simon Sherratt, Nilanjan Dey, Amit Joshi
Editorial	Springer Science and Business Media Deutschland GmbH
Páginas	641-649
Número de páginas	9
ISBN (versión impresa)	9789819930425
DOI	https://doi.org/10.1007/978-981-99-3043-2_51
Estado	Publicada - 2024
Evento	8th International Congress on Information and Communication Technology, ICICT 2023 - London, Reino Unido Duración: 20 feb. 2023 → 23 feb. 2023

Serie de la publicación

Nombre	Lecture Notes in Networks and Systems
Volumen	695 LNNS
ISSN (versión impresa)	2367-3370
ISSN (versión digital)	2367-3389

Conferencia

Conferencia	8th International Congress on Information and Communication Technology, ICICT 2023
País/Territorio	Reino Unido
Ciudad	London
Período	20/02/23 → 23/02/23

Nota bibliográfica

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

Acceder al documento

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

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

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. En 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. En 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, Reino Unido, 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).

Producción científica: Capítulo del libro/informe/acta de congreso › Contribución de conferencia › revisión exhaustiva

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. En Yang XS, Sherratt RS, Dey N, Joshi A, editores, 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

Resumen

Serie de la publicación

Conferencia

Nota bibliográfica

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto