Speech robot mimicking human articulatory motion

Kotaro Fukui, Toshihiro Kusano, Yoshikazu Mukaeda, Yuto Suzuki, Atsuo Takanishi, Masaaki Honda

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

4 Citations (Scopus)

Abstract

We have developed a mechanical talking robot, Waseda Talker No. 7 Refined II, to study the human speech mechanism. The conventional control method for this robot is based on a concatenation rule of the phoneme-specific articulatory configurations. With this method, the speech mechanism of the robot is much slower than is required for human speech, because the robot requires momentary movement of motors. To resolve this problem, we have developed a control method that mimics human articulatory trajectory data. The human trajectory data for continuous speech was obtained by using an electromagnetic articulography (EMA) system. The EMA data was converted to the robot control parameters by applying inverse kinematics as well as geometric transformation. Experimental results show that the robot can produce continuous speech with human-like speed and smooth movement.

Original languageEnglish
Title of host publicationProceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
Pages1021-1024
Number of pages4
Publication statusPublished - 2010
Event11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 - Makuhari, Chiba
Duration: 2010 Sep 262010 Sep 30

Other

Other11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010
CityMakuhari, Chiba
Period10/9/2610/9/30

Fingerprint

Electromagnetic Phenomena
Biomechanical Phenomena
Robot
Continuous Speech
Human Speech
Electromagnetic
Trajectory
Talkers
Phoneme
Kinematics
Conventional

Keywords

  • EMA
  • Speech production
  • Talking robot

ASJC Scopus subject areas

  • Language and Linguistics
  • Speech and Hearing

Cite this

Fukui, K., Kusano, T., Mukaeda, Y., Suzuki, Y., Takanishi, A., & Honda, M. (2010). Speech robot mimicking human articulatory motion. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 (pp. 1021-1024)

Speech robot mimicking human articulatory motion. / Fukui, Kotaro; Kusano, Toshihiro; Mukaeda, Yoshikazu; Suzuki, Yuto; Takanishi, Atsuo; Honda, Masaaki.

Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. 2010. p. 1021-1024.

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

Fukui, K, Kusano, T, Mukaeda, Y, Suzuki, Y, Takanishi, A & Honda, M 2010, Speech robot mimicking human articulatory motion. in Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. pp. 1021-1024, 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, Makuhari, Chiba, 10/9/26.
Fukui K, Kusano T, Mukaeda Y, Suzuki Y, Takanishi A, Honda M. Speech robot mimicking human articulatory motion. In Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. 2010. p. 1021-1024
Fukui, Kotaro ; Kusano, Toshihiro ; Mukaeda, Yoshikazu ; Suzuki, Yuto ; Takanishi, Atsuo ; Honda, Masaaki. / Speech robot mimicking human articulatory motion. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010. 2010. pp. 1021-1024
@inproceedings{90be74ff3f354fe586c4c95d51a32a75,
title = "Speech robot mimicking human articulatory motion",
abstract = "We have developed a mechanical talking robot, Waseda Talker No. 7 Refined II, to study the human speech mechanism. The conventional control method for this robot is based on a concatenation rule of the phoneme-specific articulatory configurations. With this method, the speech mechanism of the robot is much slower than is required for human speech, because the robot requires momentary movement of motors. To resolve this problem, we have developed a control method that mimics human articulatory trajectory data. The human trajectory data for continuous speech was obtained by using an electromagnetic articulography (EMA) system. The EMA data was converted to the robot control parameters by applying inverse kinematics as well as geometric transformation. Experimental results show that the robot can produce continuous speech with human-like speed and smooth movement.",
keywords = "EMA, Speech production, Talking robot",
author = "Kotaro Fukui and Toshihiro Kusano and Yoshikazu Mukaeda and Yuto Suzuki and Atsuo Takanishi and Masaaki Honda",
year = "2010",
language = "English",
pages = "1021--1024",
booktitle = "Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010",

}

TY - GEN

T1 - Speech robot mimicking human articulatory motion

AU - Fukui, Kotaro

AU - Kusano, Toshihiro

AU - Mukaeda, Yoshikazu

AU - Suzuki, Yuto

AU - Takanishi, Atsuo

AU - Honda, Masaaki

PY - 2010

Y1 - 2010

N2 - We have developed a mechanical talking robot, Waseda Talker No. 7 Refined II, to study the human speech mechanism. The conventional control method for this robot is based on a concatenation rule of the phoneme-specific articulatory configurations. With this method, the speech mechanism of the robot is much slower than is required for human speech, because the robot requires momentary movement of motors. To resolve this problem, we have developed a control method that mimics human articulatory trajectory data. The human trajectory data for continuous speech was obtained by using an electromagnetic articulography (EMA) system. The EMA data was converted to the robot control parameters by applying inverse kinematics as well as geometric transformation. Experimental results show that the robot can produce continuous speech with human-like speed and smooth movement.

AB - We have developed a mechanical talking robot, Waseda Talker No. 7 Refined II, to study the human speech mechanism. The conventional control method for this robot is based on a concatenation rule of the phoneme-specific articulatory configurations. With this method, the speech mechanism of the robot is much slower than is required for human speech, because the robot requires momentary movement of motors. To resolve this problem, we have developed a control method that mimics human articulatory trajectory data. The human trajectory data for continuous speech was obtained by using an electromagnetic articulography (EMA) system. The EMA data was converted to the robot control parameters by applying inverse kinematics as well as geometric transformation. Experimental results show that the robot can produce continuous speech with human-like speed and smooth movement.

KW - EMA

KW - Speech production

KW - Talking robot

UR - http://www.scopus.com/inward/record.url?scp=79959846571&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959846571&partnerID=8YFLogxK

M3 - Conference contribution

SP - 1021

EP - 1024

BT - Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

ER -