Extraction of expression from Japanese speech based on time-frequency and fractal features

Author

Phothisonothai, Montri ; Arita, Yoshihiko ; Watanabe, K.

Author_Institution

Res. Center for Adv. Sci. & Technol., Univ. of Tokyo, Tokyo, Japan

fYear

2013

fDate

15-17 May 2013

Firstpage

1

Lastpage

5

Abstract

The extraction method based on time-frequency and fractal features was proposed to analyze intonations from Japanese speech signal. Two parameters were presented to reveal different feature patterns: Peak spectrum (F max) and Fractal dimension (FD) trajectories. The F max and FD were computed by using short-time Fourier transform (STFT) and Higuchi´s method, respectively. Speech data recorded from 15 Japanese utterances, 4 different ways of expression (accosting, wholehearted, normal, and uninterested). The results showed that the proposed features could extract different intonations statistically in comparison with baseline intonation.

Keywords

Fourier transforms; feature extraction; fractals; natural language processing; signal processing; spectral analysis; speech processing; time-frequency analysis; FD trajectory; Higuchi method; Japanese speech signal; Japanese utterances; STFT; baseline intonation; feature patterns; fractal dimension trajectory; fractal feature extraction method; intonations; peak spectrum; short-time Fourier transform; speech data; time-frequency feature; Computational modeling; Feature extraction; Fractals; IEL; Speech; Time-frequency analysis; Expression; Fractals; Intonation; Physiological reaction; Speech; Time-frequency;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), 2013 10th International Conference on

Conference_Location

Krabi

Print_ISBN

978-1-4799-0546-1

Type

conf

DOI

10.1109/ECTICon.2013.6559535

Filename

6559535