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

Montri Phothisonothai, Yasunori Arita, Katsumi Watanabe

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

1 Citation (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
Externally publishedYes
Event2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2013 - Krabi, Thailand
Duration: 2013 May 152013 May 17

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

Fractal dimension
Fractals
Fourier transforms
Trajectories

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] https://doi.org/10.1109/ECTICon.2013.6559535

Extraction of expression from Japanese speech based on time-frequency and fractal features. / Phothisonothai, Montri; Arita, Yasunori; Watanabe, Katsumi.

2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2013. 2013. 6559535.

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

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, Krabi, Thailand, 13/5/15. https://doi.org/10.1109/ECTICon.2013.6559535
Phothisonothai M, Arita Y, Watanabe K. 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. 2013. 6559535 https://doi.org/10.1109/ECTICon.2013.6559535
Phothisonothai, Montri ; Arita, Yasunori ; Watanabe, Katsumi. / Extraction of expression from Japanese speech based on time-frequency and fractal features. 2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2013. 2013.
@inproceedings{e82b4e06ca72437aaca48f61698db911,
title = "Extraction of expression from Japanese speech based on time-frequency and fractal features",
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.",
keywords = "Expression, Fractals, Intonation, Physiological reaction, Speech, Time-frequency",
author = "Montri Phothisonothai and Yasunori Arita and Katsumi Watanabe",
year = "2013",
doi = "10.1109/ECTICon.2013.6559535",
language = "English",
isbn = "9781479905454",
booktitle = "2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2013",

}

TY - GEN

T1 - Extraction of expression from Japanese speech based on time-frequency and fractal features

AU - Phothisonothai, Montri

AU - Arita, Yasunori

AU - Watanabe, Katsumi

PY - 2013

Y1 - 2013

N2 - 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.

AB - 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.

KW - Expression

KW - Fractals

KW - Intonation

KW - Physiological reaction

KW - Speech

KW - Time-frequency

UR - http://www.scopus.com/inward/record.url?scp=84883102604&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883102604&partnerID=8YFLogxK

U2 - 10.1109/ECTICon.2013.6559535

DO - 10.1109/ECTICon.2013.6559535

M3 - Conference contribution

AN - SCOPUS:84883102604

SN - 9781479905454

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

ER -