Double Fourier analysis for Emotion Identification in Voiced Speech

20th Argentinean Bioengineering Society Congress

物理学;生物科学

Sierra-Sosa, D.^1 ; Bastidas, M.^1 ; Ortiz, P.D.^1 ; Quintero, O.L.^1

Mathematical Modeling Research Group, GRIMMAT, School of Sciences, Universidad EAFIT, Carrera 49 No 7 Sur-50, Medellin, Colombia^1

关键词: Emotion identifications;    Emotion recognition from speech;    Gaussian window;    Quasi-periodic;    Short time Fourier transforms;    Spatial Fourier analysis;    Time-frequency distributions;    Vocal tract resonances;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/705/1/012035/pdf
DOI  :  10.1088/1742-6596/705/1/012035

学科分类：生物科学（综合）

来源: IOP

【 摘 要 】

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.