Control methods based on neural network forward and inverse models for a biomechanical structured vocal cord model on an anthropomorphic talking robot

Kotaro Fukui, Eiji Shintaku, Akihiro Shimomura, Nana Sakakibara, Yuma Ishikawa, Masaaki Honda, Atsuo Takanishi

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

1 Citation (Scopus)

Abstract

We have developed a vocal control method, based on forward and inverse models, to allow the anthropomorphic talking robot Waseda Talker No. 7 (WT-7) to produce various kinds of voices. The control parameters of the vocal cords on WT-7 are pressure, vocal cord tension and glottal opening, and the acoustic parameters are sound pressure, sound pitch and spectrum slope. The relationships among these parameters are complicated and difficult to model using conventional methods. Here we present a neural network (NN) control method. The learning process consists of creation of the NN forward model by back propagation methods and optimization of the inverse model using the forward model. In addition, a real-time auditory feed-back mechanism is used to reduce the error between the target and the generated acoustic parameters. Using this method, the control parameters can be adjusted to follow the target voice well.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Pages3648-3653
Number of pages6
DOIs
Publication statusPublished - 2008
Event2008 IEEE International Conference on Robotics and Automation, ICRA 2008 - Pasadena, CA
Duration: 2008 May 192008 May 23

Other

Other2008 IEEE International Conference on Robotics and Automation, ICRA 2008
CityPasadena, CA
Period08/5/1908/5/23

Fingerprint

Anthropomorphic robots
Neural networks
Acoustics
Acoustic waves
Backpropagation
Feedback

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering

Cite this

Fukui, K., Shintaku, E., Shimomura, A., Sakakibara, N., Ishikawa, Y., Honda, M., & Takanishi, A. (2008). Control methods based on neural network forward and inverse models for a biomechanical structured vocal cord model on an anthropomorphic talking robot. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 3648-3653). [4543770] https://doi.org/10.1109/ROBOT.2008.4543770

Control methods based on neural network forward and inverse models for a biomechanical structured vocal cord model on an anthropomorphic talking robot. / Fukui, Kotaro; Shintaku, Eiji; Shimomura, Akihiro; Sakakibara, Nana; Ishikawa, Yuma; Honda, Masaaki; Takanishi, Atsuo.

Proceedings - IEEE International Conference on Robotics and Automation. 2008. p. 3648-3653 4543770.

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

Fukui, K, Shintaku, E, Shimomura, A, Sakakibara, N, Ishikawa, Y, Honda, M & Takanishi, A 2008, Control methods based on neural network forward and inverse models for a biomechanical structured vocal cord model on an anthropomorphic talking robot. in Proceedings - IEEE International Conference on Robotics and Automation., 4543770, pp. 3648-3653, 2008 IEEE International Conference on Robotics and Automation, ICRA 2008, Pasadena, CA, 08/5/19. https://doi.org/10.1109/ROBOT.2008.4543770
Fukui K, Shintaku E, Shimomura A, Sakakibara N, Ishikawa Y, Honda M et al. Control methods based on neural network forward and inverse models for a biomechanical structured vocal cord model on an anthropomorphic talking robot. In Proceedings - IEEE International Conference on Robotics and Automation. 2008. p. 3648-3653. 4543770 https://doi.org/10.1109/ROBOT.2008.4543770
Fukui, Kotaro ; Shintaku, Eiji ; Shimomura, Akihiro ; Sakakibara, Nana ; Ishikawa, Yuma ; Honda, Masaaki ; Takanishi, Atsuo. / Control methods based on neural network forward and inverse models for a biomechanical structured vocal cord model on an anthropomorphic talking robot. Proceedings - IEEE International Conference on Robotics and Automation. 2008. pp. 3648-3653
@inproceedings{c7a3284b51de47ec94d00bab012432ec,
title = "Control methods based on neural network forward and inverse models for a biomechanical structured vocal cord model on an anthropomorphic talking robot",
abstract = "We have developed a vocal control method, based on forward and inverse models, to allow the anthropomorphic talking robot Waseda Talker No. 7 (WT-7) to produce various kinds of voices. The control parameters of the vocal cords on WT-7 are pressure, vocal cord tension and glottal opening, and the acoustic parameters are sound pressure, sound pitch and spectrum slope. The relationships among these parameters are complicated and difficult to model using conventional methods. Here we present a neural network (NN) control method. The learning process consists of creation of the NN forward model by back propagation methods and optimization of the inverse model using the forward model. In addition, a real-time auditory feed-back mechanism is used to reduce the error between the target and the generated acoustic parameters. Using this method, the control parameters can be adjusted to follow the target voice well.",
author = "Kotaro Fukui and Eiji Shintaku and Akihiro Shimomura and Nana Sakakibara and Yuma Ishikawa and Masaaki Honda and Atsuo Takanishi",
year = "2008",
doi = "10.1109/ROBOT.2008.4543770",
language = "English",
isbn = "9781424416479",
pages = "3648--3653",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

}

TY - GEN

T1 - Control methods based on neural network forward and inverse models for a biomechanical structured vocal cord model on an anthropomorphic talking robot

AU - Fukui, Kotaro

AU - Shintaku, Eiji

AU - Shimomura, Akihiro

AU - Sakakibara, Nana

AU - Ishikawa, Yuma

AU - Honda, Masaaki

AU - Takanishi, Atsuo

PY - 2008

Y1 - 2008

N2 - We have developed a vocal control method, based on forward and inverse models, to allow the anthropomorphic talking robot Waseda Talker No. 7 (WT-7) to produce various kinds of voices. The control parameters of the vocal cords on WT-7 are pressure, vocal cord tension and glottal opening, and the acoustic parameters are sound pressure, sound pitch and spectrum slope. The relationships among these parameters are complicated and difficult to model using conventional methods. Here we present a neural network (NN) control method. The learning process consists of creation of the NN forward model by back propagation methods and optimization of the inverse model using the forward model. In addition, a real-time auditory feed-back mechanism is used to reduce the error between the target and the generated acoustic parameters. Using this method, the control parameters can be adjusted to follow the target voice well.

AB - We have developed a vocal control method, based on forward and inverse models, to allow the anthropomorphic talking robot Waseda Talker No. 7 (WT-7) to produce various kinds of voices. The control parameters of the vocal cords on WT-7 are pressure, vocal cord tension and glottal opening, and the acoustic parameters are sound pressure, sound pitch and spectrum slope. The relationships among these parameters are complicated and difficult to model using conventional methods. Here we present a neural network (NN) control method. The learning process consists of creation of the NN forward model by back propagation methods and optimization of the inverse model using the forward model. In addition, a real-time auditory feed-back mechanism is used to reduce the error between the target and the generated acoustic parameters. Using this method, the control parameters can be adjusted to follow the target voice well.

UR - http://www.scopus.com/inward/record.url?scp=51649105997&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51649105997&partnerID=8YFLogxK

U2 - 10.1109/ROBOT.2008.4543770

DO - 10.1109/ROBOT.2008.4543770

M3 - Conference contribution

SN - 9781424416479

SP - 3648

EP - 3653

BT - Proceedings - IEEE International Conference on Robotics and Automation

ER -