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

Montri Phothisonothai, Yasunori Arita, Kat Watanabe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

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 (Fmax) and Fractal dimension (FD) trajectories. The Fmax 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.

Original languageEnglish
Title of host publication2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2013
DOIs
Publication statusPublished - 2013 Sep 2
Event2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2013 - Krabi, Thailand
Duration: 2013 May 152013 May 17

Publication series

Name2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2013

Other

Other2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2013
CountryThailand
CityKrabi
Period13/5/1513/5/17

    Fingerprint

Keywords

  • Expression
  • Fractals
  • Intonation
  • Physiological reaction
  • Speech
  • Time-frequency

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Cite this

Phothisonothai, M., Arita, Y., & Watanabe, K. (2013). Extraction of expression from Japanese speech based on time-frequency and fractal features. In 2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2013 [6559535] (2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2013). https://doi.org/10.1109/ECTICon.2013.6559535