A taking robot for the vocal communication by the mimicry of human voice

Mitsuki Kitani, Tatsuya Hara, Hiroki Hanada, Hideyuki Sawada

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

1 Citation (Scopus)

Abstract

A talking and singing robot which adaptively learns the vocalization skill by an auditory feedback learning is being developed. The fundamental frequency and the spectrum envelope determine the principal characteristics of a sound. The former is the characteristic of a source sound generated by a vibrating object, and the latter is operated by the work of the resonance effects. In vocalization, the vibration of vocal cords generates a source sound, and then the sound wave is led to a vocal tract, which works as a resonance filter to determine the spectrum envelope. The paper describes the construction of vocal cords and a vocal tract for the realization of a talking and singing robot, together with the control algorithm for the acquisition of singing performance by mimicking human vocalization and singing voices. Generated voices were evaluated by listening experiments.

Original languageEnglish
Title of host publication3rd International Conference on Human System Interaction, HSI'2010 - Conference Proceedings
Pages728-733
Number of pages6
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event3rd International Conference on Human System Interaction, HSI'2010 - Rzeszow
Duration: 2010 May 132010 May 15

Other

Other3rd International Conference on Human System Interaction, HSI'2010
CityRzeszow
Period10/5/1310/5/15

Fingerprint

Acoustic waves
Robots
Communication
Vibrations (mechanical)
Feedback
Experiments

Keywords

  • Adaptive learning
  • Neural network
  • Singing performance
  • Talking robot
  • Vocal cords
  • Vocal tract

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Software

Cite this

Kitani, M., Hara, T., Hanada, H., & Sawada, H. (2010). A taking robot for the vocal communication by the mimicry of human voice. In 3rd International Conference on Human System Interaction, HSI'2010 - Conference Proceedings (pp. 728-733). [5514489] https://doi.org/10.1109/HSI.2010.5514489

A taking robot for the vocal communication by the mimicry of human voice. / Kitani, Mitsuki; Hara, Tatsuya; Hanada, Hiroki; Sawada, Hideyuki.

3rd International Conference on Human System Interaction, HSI'2010 - Conference Proceedings. 2010. p. 728-733 5514489.

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

Kitani, M, Hara, T, Hanada, H & Sawada, H 2010, A taking robot for the vocal communication by the mimicry of human voice. in 3rd International Conference on Human System Interaction, HSI'2010 - Conference Proceedings., 5514489, pp. 728-733, 3rd International Conference on Human System Interaction, HSI'2010, Rzeszow, 10/5/13. https://doi.org/10.1109/HSI.2010.5514489
Kitani M, Hara T, Hanada H, Sawada H. A taking robot for the vocal communication by the mimicry of human voice. In 3rd International Conference on Human System Interaction, HSI'2010 - Conference Proceedings. 2010. p. 728-733. 5514489 https://doi.org/10.1109/HSI.2010.5514489
Kitani, Mitsuki ; Hara, Tatsuya ; Hanada, Hiroki ; Sawada, Hideyuki. / A taking robot for the vocal communication by the mimicry of human voice. 3rd International Conference on Human System Interaction, HSI'2010 - Conference Proceedings. 2010. pp. 728-733
@inproceedings{a7965641b392408ea31a86ccfab47b59,
title = "A taking robot for the vocal communication by the mimicry of human voice",
abstract = "A talking and singing robot which adaptively learns the vocalization skill by an auditory feedback learning is being developed. The fundamental frequency and the spectrum envelope determine the principal characteristics of a sound. The former is the characteristic of a source sound generated by a vibrating object, and the latter is operated by the work of the resonance effects. In vocalization, the vibration of vocal cords generates a source sound, and then the sound wave is led to a vocal tract, which works as a resonance filter to determine the spectrum envelope. The paper describes the construction of vocal cords and a vocal tract for the realization of a talking and singing robot, together with the control algorithm for the acquisition of singing performance by mimicking human vocalization and singing voices. Generated voices were evaluated by listening experiments.",
keywords = "Adaptive learning, Neural network, Singing performance, Talking robot, Vocal cords, Vocal tract",
author = "Mitsuki Kitani and Tatsuya Hara and Hiroki Hanada and Hideyuki Sawada",
year = "2010",
doi = "10.1109/HSI.2010.5514489",
language = "English",
isbn = "9781424475605",
pages = "728--733",
booktitle = "3rd International Conference on Human System Interaction, HSI'2010 - Conference Proceedings",

}

TY - GEN

T1 - A taking robot for the vocal communication by the mimicry of human voice

AU - Kitani, Mitsuki

AU - Hara, Tatsuya

AU - Hanada, Hiroki

AU - Sawada, Hideyuki

PY - 2010

Y1 - 2010

N2 - A talking and singing robot which adaptively learns the vocalization skill by an auditory feedback learning is being developed. The fundamental frequency and the spectrum envelope determine the principal characteristics of a sound. The former is the characteristic of a source sound generated by a vibrating object, and the latter is operated by the work of the resonance effects. In vocalization, the vibration of vocal cords generates a source sound, and then the sound wave is led to a vocal tract, which works as a resonance filter to determine the spectrum envelope. The paper describes the construction of vocal cords and a vocal tract for the realization of a talking and singing robot, together with the control algorithm for the acquisition of singing performance by mimicking human vocalization and singing voices. Generated voices were evaluated by listening experiments.

AB - A talking and singing robot which adaptively learns the vocalization skill by an auditory feedback learning is being developed. The fundamental frequency and the spectrum envelope determine the principal characteristics of a sound. The former is the characteristic of a source sound generated by a vibrating object, and the latter is operated by the work of the resonance effects. In vocalization, the vibration of vocal cords generates a source sound, and then the sound wave is led to a vocal tract, which works as a resonance filter to determine the spectrum envelope. The paper describes the construction of vocal cords and a vocal tract for the realization of a talking and singing robot, together with the control algorithm for the acquisition of singing performance by mimicking human vocalization and singing voices. Generated voices were evaluated by listening experiments.

KW - Adaptive learning

KW - Neural network

KW - Singing performance

KW - Talking robot

KW - Vocal cords

KW - Vocal tract

UR - http://www.scopus.com/inward/record.url?scp=77955670141&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955670141&partnerID=8YFLogxK

U2 - 10.1109/HSI.2010.5514489

DO - 10.1109/HSI.2010.5514489

M3 - Conference contribution

AN - SCOPUS:77955670141

SN - 9781424475605

SP - 728

EP - 733

BT - 3rd International Conference on Human System Interaction, HSI'2010 - Conference Proceedings

ER -