Aviation Profiling Method Based on Deep Learning Technology for Emotion Recognition by Speech Signal

This paper proposes a method of automatic speaker-independent recognition of human psycho-emotional states by analyzing the speech signal based on Deep Learning technology to solve the problems of aviation profiling. For this purpose, an algorithm to classify seven human psycho-emotional states, inc...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Koshekov К.Т., Savostin А.А., Seidakhmetov B.K., Anayatova R.K., Fedorov I.O.
Formato:	article
Lenguaje:	EN
Publicado:	Sciendo 2021
Materias:	aviation profiling emotion recognition speech signal neural network Transportation and communication K4011-4343
Acceso en línea:	https://doaj.org/article/f3786aa2b4644fd4a079b9bc8b438ede
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f3786aa2b4644fd4a079b9bc8b438ede
record_format	dspace
spelling	oai:doaj.org-article:f3786aa2b4644fd4a079b9bc8b438ede2021-12-05T14:11:11ZAviation Profiling Method Based on Deep Learning Technology for Emotion Recognition by Speech Signal1407-617910.2478/ttj-2021-0037https://doaj.org/article/f3786aa2b4644fd4a079b9bc8b438ede2021-11-01T00:00:00Zhttps://doi.org/10.2478/ttj-2021-0037https://doaj.org/toc/1407-6179This paper proposes a method of automatic speaker-independent recognition of human psycho-emotional states by analyzing the speech signal based on Deep Learning technology to solve the problems of aviation profiling. For this purpose, an algorithm to classify seven human psycho-emotional states, including anger, joy, fear, surprise, disgust, sadness, and neutral state was developed. The algorithm is based on the use of Mel-frequency cepstral coefficients and Mel spectrograms as informative features of speech signals audio recordings. These informative features are used to train two deep convolutional neural networks on the generated dataset. The developed classifier testing on a delayed verification dataset showed that the metric for the multiclass fraction of correct answers’ accuracy is 0.93. The solution proposed in the paper can be in demand in human-machine interfaces creation, medicine, marketing, and in the field of air transportation.Koshekov К.Т.Savostin А.А.Seidakhmetov B.K.Anayatova R.K.Fedorov I.O.Sciendoarticleaviation profilingemotion recognitionspeech signalneural networkTransportation and communicationK4011-4343ENTransport and Telecommunication, Vol 22, Iss 4, Pp 471-481 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	aviation profiling emotion recognition speech signal neural network Transportation and communication K4011-4343
spellingShingle	aviation profiling emotion recognition speech signal neural network Transportation and communication K4011-4343 Koshekov К.Т. Savostin А.А. Seidakhmetov B.K. Anayatova R.K. Fedorov I.O. Aviation Profiling Method Based on Deep Learning Technology for Emotion Recognition by Speech Signal
description	This paper proposes a method of automatic speaker-independent recognition of human psycho-emotional states by analyzing the speech signal based on Deep Learning technology to solve the problems of aviation profiling. For this purpose, an algorithm to classify seven human psycho-emotional states, including anger, joy, fear, surprise, disgust, sadness, and neutral state was developed. The algorithm is based on the use of Mel-frequency cepstral coefficients and Mel spectrograms as informative features of speech signals audio recordings. These informative features are used to train two deep convolutional neural networks on the generated dataset. The developed classifier testing on a delayed verification dataset showed that the metric for the multiclass fraction of correct answers’ accuracy is 0.93. The solution proposed in the paper can be in demand in human-machine interfaces creation, medicine, marketing, and in the field of air transportation.
format	article
author	Koshekov К.Т. Savostin А.А. Seidakhmetov B.K. Anayatova R.K. Fedorov I.O.
author_facet	Koshekov К.Т. Savostin А.А. Seidakhmetov B.K. Anayatova R.K. Fedorov I.O.
author_sort	Koshekov К.Т.
title	Aviation Profiling Method Based on Deep Learning Technology for Emotion Recognition by Speech Signal
title_short	Aviation Profiling Method Based on Deep Learning Technology for Emotion Recognition by Speech Signal
title_full	Aviation Profiling Method Based on Deep Learning Technology for Emotion Recognition by Speech Signal
title_fullStr	Aviation Profiling Method Based on Deep Learning Technology for Emotion Recognition by Speech Signal
title_full_unstemmed	Aviation Profiling Method Based on Deep Learning Technology for Emotion Recognition by Speech Signal
title_sort	aviation profiling method based on deep learning technology for emotion recognition by speech signal
publisher	Sciendo
publishDate	2021
url	https://doaj.org/article/f3786aa2b4644fd4a079b9bc8b438ede
work_keys_str_mv	AT koshekovkt aviationprofilingmethodbasedondeeplearningtechnologyforemotionrecognitionbyspeechsignal AT savostinaa aviationprofilingmethodbasedondeeplearningtechnologyforemotionrecognitionbyspeechsignal AT seidakhmetovbk aviationprofilingmethodbasedondeeplearningtechnologyforemotionrecognitionbyspeechsignal AT anayatovark aviationprofilingmethodbasedondeeplearningtechnologyforemotionrecognitionbyspeechsignal AT fedorovio aviationprofilingmethodbasedondeeplearningtechnologyforemotionrecognitionbyspeechsignal
_version_	1718371333019009024

Aviation Profiling Method Based on Deep Learning Technology for Emotion Recognition by Speech Signal

Ejemplares similares