Multiresolution analysis (discrete wavelet transform) through Daubechies family for emotion recognition in speech


Autoria(s): Campo, D.; Quintero, O.L.; Bastidas, M
Contribuinte(s)

Universidad EAFIT. Escuela de Ciencias. Grupo de Investigación Modelado Matemático

dcampoc@eafit.edu.co

oquinte1@eafit.edu.co

mbastida@eafit.edu.co

Dipartimento di Ingegneria Navale, Elettrica, Elettronica e delle Telecomunicazioni (DITEN). Information and Signal Processing for Cognitive Telecommunications ISIP40, Genova, Italy

Mathematical Modeling Research Group at Mathematical Sciences Department in School of Sciences at Universidad EAFIT, Medellín, Colombia

Data(s)

2016

11/05/2016

2016

11/05/2016

Resumo

We propose a study of the mathematical properties of voice as an audio signal -- This work includes signals in which the channel conditions are not ideal for emotion recognition -- Multiresolution analysis- discrete wavelet transform – was performed through the use of Daubechies Wavelet Family (Db1-Haar, Db6, Db8, Db10) allowing the decomposition of the initial audio signal into sets of coefficients on which a set of features was extracted and analyzed statistically in order to differentiate emotional states -- ANNs proved to be a system that allows an appropriate classification of such states -- This study shows that the extracted features using wavelet decomposition are enough to analyze and extract emotional content in audio signals presenting a high accuracy rate in classification of emotional states without the need to use other kinds of classical frequency-time features -- Accordingly, this paper seeks to characterize mathematically the six basic emotions in humans: boredom, disgust, happiness, anxiety, anger and sadness, also included the neutrality, for a total of seven states to identify

20th Argentinean Bioengineering Society Congress, SABI 2015 (XX Congreso Argentino de Bioingeniería y IX Jornadas de Ingeniería Clínica)28–30 October 2015, San Nicolás de los Arroyos, Argentina

Formato

application/pdf

Identificador

1742-6596

http://dx.doi.org/10.1088/1742-6596/705/1/012034

http://hdl.handle.net/10784/8374

10.1088/1742-6596/705/1/012034

Idioma(s)

eng

Publicador

IOP Publishing

Relação

Journal of Physics: Conference Series; Vol. 705, Núm. 1 (2016); pp.7

http://dx.doi.org/10.1088/1742-6596/705/1/012034

Direitos

info:eu-repo/semantics/openAccess

openAccess

Libre acceso

Creative Commons Attribution 3.0 licence (CC BY 3.0)

Fonte

Journal of Physics: Conference Series; Vol. 705, Núm. 1 (2016); pp.7

Palavras-Chave #Transformadas de Wavelet #Análisis Multi - Resolución #Procesamiento digital de voz #RECONOCIMIENTO AUTOMÁTICO DE LA VOZ #PROCESAMIENTO DE SEÑALES #INTELIGENCIA ARTIFICIAL #EMOCIONES #ANÁLISIS ESPECTRAL #REDES NEURALES (COMPUTADORES) #ANÁLISIS DE FOURIER #INTELIGENCIA ARTIFICIAL #Automatic speech recognition #Signal processing #Artificial intelligence #Emotions #Spectrum analysis #Neural networks (Computer science) #Fourier analysis #Artificial intelligence
Tipo

info:eu-repo/semantics/article

info:eu-repo/semantics/publishedVersion

article

Artículo