The log-Gabor method: speech classification using spectrogram image analysis

We explored the suitability of the log-Gabor method, a speech analysis method inspired by Ezzat e.a. (2007), for automatic classification of personality and likability traits in speech. The core idea underlying the log-Gabor method is to treat the spectrogram as an image of spectro-temporal information. The image is transformed into Gabor energy values using the twodimensional logarithmic Gabor transform, which is a standard feature extraction method in visual texture analysis. The aggregated energy values are mapped onto classes by means of a support vector machine (SVM). The log-Gabor method performed above baseline on the INTERSPEECH Personality and Likability Sub-Challenges Development sets and comparable to baseline for the Test sets. These results support further investigation of the log-Gabor method as a method for extracting perceptual cues from speech.