Cargando…

On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition

Many speech emotion recognition systems have been designed using different features and classification methods. Still, there is a lack of knowledge and reasoning regarding the underlying speech characteristics and processing, i.e., how basic characteristics, methods, and settings affect the accuracy...

Descripción completa

Detalles Bibliográficos
Autores principales: Kacur, Juraj, Puterka, Boris, Pavlovicova, Jarmila, Oravec, Milos
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7962835/
https://www.ncbi.nlm.nih.gov/pubmed/33800348
http://dx.doi.org/10.3390/s21051888
_version_ 1783665530881703936
author Kacur, Juraj
Puterka, Boris
Pavlovicova, Jarmila
Oravec, Milos
author_facet Kacur, Juraj
Puterka, Boris
Pavlovicova, Jarmila
Oravec, Milos
author_sort Kacur, Juraj
collection PubMed
description Many speech emotion recognition systems have been designed using different features and classification methods. Still, there is a lack of knowledge and reasoning regarding the underlying speech characteristics and processing, i.e., how basic characteristics, methods, and settings affect the accuracy, to what extent, etc. This study is to extend physical perspective on speech emotion recognition by analyzing basic speech characteristics and modeling methods, e.g., time characteristics (segmentation, window types, and classification regions—lengths and overlaps), frequency ranges, frequency scales, processing of whole speech (spectrograms), vocal tract (filter banks, linear prediction coefficient (LPC) modeling), and excitation (inverse LPC filtering) signals, magnitude and phase manipulations, cepstral features, etc. In the evaluation phase the state-of-the-art classification method and rigorous statistical tests were applied, namely N-fold cross validation, paired t-test, rank, and Pearson correlations. The results revealed several settings in a 75% accuracy range (seven emotions). The most successful methods were based on vocal tract features using psychoacoustic filter banks covering the 0–8 kHz frequency range. Well scoring are also spectrograms carrying vocal tract and excitation information. It was found that even basic processing like pre-emphasis, segmentation, magnitude modifications, etc., can dramatically affect the results. Most findings are robust by exhibiting strong correlations across tested databases.
format Online
Article
Text
id pubmed-7962835
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-79628352021-03-17 On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition Kacur, Juraj Puterka, Boris Pavlovicova, Jarmila Oravec, Milos Sensors (Basel) Article Many speech emotion recognition systems have been designed using different features and classification methods. Still, there is a lack of knowledge and reasoning regarding the underlying speech characteristics and processing, i.e., how basic characteristics, methods, and settings affect the accuracy, to what extent, etc. This study is to extend physical perspective on speech emotion recognition by analyzing basic speech characteristics and modeling methods, e.g., time characteristics (segmentation, window types, and classification regions—lengths and overlaps), frequency ranges, frequency scales, processing of whole speech (spectrograms), vocal tract (filter banks, linear prediction coefficient (LPC) modeling), and excitation (inverse LPC filtering) signals, magnitude and phase manipulations, cepstral features, etc. In the evaluation phase the state-of-the-art classification method and rigorous statistical tests were applied, namely N-fold cross validation, paired t-test, rank, and Pearson correlations. The results revealed several settings in a 75% accuracy range (seven emotions). The most successful methods were based on vocal tract features using psychoacoustic filter banks covering the 0–8 kHz frequency range. Well scoring are also spectrograms carrying vocal tract and excitation information. It was found that even basic processing like pre-emphasis, segmentation, magnitude modifications, etc., can dramatically affect the results. Most findings are robust by exhibiting strong correlations across tested databases. MDPI 2021-03-08 /pmc/articles/PMC7962835/ /pubmed/33800348 http://dx.doi.org/10.3390/s21051888 Text en © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kacur, Juraj
Puterka, Boris
Pavlovicova, Jarmila
Oravec, Milos
On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition
title On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition
title_full On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition
title_fullStr On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition
title_full_unstemmed On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition
title_short On the Speech Properties and Feature Extraction Methods in Speech Emotion Recognition
title_sort on the speech properties and feature extraction methods in speech emotion recognition
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7962835/
https://www.ncbi.nlm.nih.gov/pubmed/33800348
http://dx.doi.org/10.3390/s21051888
work_keys_str_mv AT kacurjuraj onthespeechpropertiesandfeatureextractionmethodsinspeechemotionrecognition
AT puterkaboris onthespeechpropertiesandfeatureextractionmethodsinspeechemotionrecognition
AT pavlovicovajarmila onthespeechpropertiesandfeatureextractionmethodsinspeechemotionrecognition
AT oravecmilos onthespeechpropertiesandfeatureextractionmethodsinspeechemotionrecognition