Double Fourier analysis for Emotion Identification in Voiced Speech

We propose a novel analysis alternative, based on two Fourier Transforms for emotion recognition from speech -- Fourier analysis allows for display and synthesizes different signals, in terms of power spectral density distributions -- A spectrogram of the voice signal is obtained performing a short...

Full description

Autores:
Sierra-Sosa, D
Bastidas, M
Ortiz P., D.
Quintero, O.L.
Sierra-Sosa, D
Bastidas, M
Ortiz P., D.
Quintero, O.L.
Tipo de recurso:
Fecha de publicación:
2016
Institución:
Universidad EAFIT
Repositorio:
Repositorio EAFIT
Idioma:
eng
OAI Identifier:
oai:repository.eafit.edu.co:10784/8375
Acceso en línea:
http://hdl.handle.net/10784/8375
Palabra clave:
Transformadas de Wavelet
Procesamiento digital de voz
Morfología matemática
ANÁLISIS ESPECTRAL
ANÁLISIS DE FOURIER
PROCESAMIENTO DE SEÑALES
SISTEMAS DE PROCESAMIENTO DE LA VOZ
TRANSFORMACIONES (MATEMÁTICAS)
PRINCIPIO DE INCERTIDUMBRE DE HEISENBERG
Spectrum analysis
Fourier analysis
Signal processing
Speech processing systems
Transformations (mathematics)
Heisenberg uncertainty principle
Spectrum analysis
Fourier analysis
Signal processing
Speech processing systems
Transformations (mathematics)
Heisenberg uncertainty principle
Transformadas de Wavelet
Procesamiento digital de voz
Morfología matemática
Rights
License
Acceso abierto
Description
Summary:We propose a novel analysis alternative, based on two Fourier Transforms for emotion recognition from speech -- Fourier analysis allows for display and synthesizes different signals, in terms of power spectral density distributions -- A spectrogram of the voice signal is obtained performing a short time Fourier Transform with Gaussian windows, this spectrogram portraits frequency related features, such as vocal tract resonances and quasi-periodic excitations during voiced sounds -- Emotions induce such characteristics in speech, which become apparent in spectrogram time-frequency distributions -- Later, the signal time-frequency representation from spectrogram is considered an image, and processed through a 2-dimensional Fourier Transform in order to perform the spatial Fourier analysis from it -- Finally features related with emotions in voiced speech are extracted and presented