Vocal imitation using physical vocal tract model

Hisashi Kanda, Tetsuya Ogata, Kazunori Komatani, Hiroshi G. Okuno

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

5 Citations (Scopus)

Abstract

A vocal imitation system was developed using a computational model that supports the motor theory of speech perception. A critical problem in vocal imitation is how to generate speech sounds produced by adults, whose vocal tracts have physical properties (i.e., articulatory motions) differing from those of infants' vocal tracts. To solve this problem, a model based on the motor theory of speech perception, was constructed. This model suggests that infants simulate the speech generation by estimating their own articulatory motions in order to interpret the speech sounds of adults. Applying this model enables the vocal imitation system to estimate articulatory motions for unexperienced speech sounds that have not actually been generated by the system. The system was implemented by using Recurrent Neural Network with Parametric Bias (RNNPB) and a physical vocal tract model, called the Maeda model. Experimental results demonstrated that the system was sufficiently robust with respect to individual differences in speech sounds and could imitate unexperienced vowel sounds.

Original languageEnglish
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Pages1846-1851
Number of pages6
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007 - San Diego, CA
Duration: 2007 Oct 292007 Nov 2

Other

Other2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007
CitySan Diego, CA
Period07/10/2907/11/2

Fingerprint

Acoustic waves
Recurrent neural networks
Physical properties

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Kanda, H., Ogata, T., Komatani, K., & Okuno, H. G. (2007). Vocal imitation using physical vocal tract model. In IEEE International Conference on Intelligent Robots and Systems (pp. 1846-1851). [4399137] https://doi.org/10.1109/IROS.2007.4399137

Vocal imitation using physical vocal tract model. / Kanda, Hisashi; Ogata, Tetsuya; Komatani, Kazunori; Okuno, Hiroshi G.

IEEE International Conference on Intelligent Robots and Systems. 2007. p. 1846-1851 4399137.

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

Kanda, H, Ogata, T, Komatani, K & Okuno, HG 2007, Vocal imitation using physical vocal tract model. in IEEE International Conference on Intelligent Robots and Systems., 4399137, pp. 1846-1851, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007, San Diego, CA, 07/10/29. https://doi.org/10.1109/IROS.2007.4399137
Kanda H, Ogata T, Komatani K, Okuno HG. Vocal imitation using physical vocal tract model. In IEEE International Conference on Intelligent Robots and Systems. 2007. p. 1846-1851. 4399137 https://doi.org/10.1109/IROS.2007.4399137
Kanda, Hisashi ; Ogata, Tetsuya ; Komatani, Kazunori ; Okuno, Hiroshi G. / Vocal imitation using physical vocal tract model. IEEE International Conference on Intelligent Robots and Systems. 2007. pp. 1846-1851
@inproceedings{d464531593224d08889cec3891b37a6d,
title = "Vocal imitation using physical vocal tract model",
abstract = "A vocal imitation system was developed using a computational model that supports the motor theory of speech perception. A critical problem in vocal imitation is how to generate speech sounds produced by adults, whose vocal tracts have physical properties (i.e., articulatory motions) differing from those of infants' vocal tracts. To solve this problem, a model based on the motor theory of speech perception, was constructed. This model suggests that infants simulate the speech generation by estimating their own articulatory motions in order to interpret the speech sounds of adults. Applying this model enables the vocal imitation system to estimate articulatory motions for unexperienced speech sounds that have not actually been generated by the system. The system was implemented by using Recurrent Neural Network with Parametric Bias (RNNPB) and a physical vocal tract model, called the Maeda model. Experimental results demonstrated that the system was sufficiently robust with respect to individual differences in speech sounds and could imitate unexperienced vowel sounds.",
author = "Hisashi Kanda and Tetsuya Ogata and Kazunori Komatani and Okuno, {Hiroshi G.}",
year = "2007",
doi = "10.1109/IROS.2007.4399137",
language = "English",
isbn = "1424409128",
pages = "1846--1851",
booktitle = "IEEE International Conference on Intelligent Robots and Systems",

}

TY - GEN

T1 - Vocal imitation using physical vocal tract model

AU - Kanda, Hisashi

AU - Ogata, Tetsuya

AU - Komatani, Kazunori

AU - Okuno, Hiroshi G.

PY - 2007

Y1 - 2007

N2 - A vocal imitation system was developed using a computational model that supports the motor theory of speech perception. A critical problem in vocal imitation is how to generate speech sounds produced by adults, whose vocal tracts have physical properties (i.e., articulatory motions) differing from those of infants' vocal tracts. To solve this problem, a model based on the motor theory of speech perception, was constructed. This model suggests that infants simulate the speech generation by estimating their own articulatory motions in order to interpret the speech sounds of adults. Applying this model enables the vocal imitation system to estimate articulatory motions for unexperienced speech sounds that have not actually been generated by the system. The system was implemented by using Recurrent Neural Network with Parametric Bias (RNNPB) and a physical vocal tract model, called the Maeda model. Experimental results demonstrated that the system was sufficiently robust with respect to individual differences in speech sounds and could imitate unexperienced vowel sounds.

AB - A vocal imitation system was developed using a computational model that supports the motor theory of speech perception. A critical problem in vocal imitation is how to generate speech sounds produced by adults, whose vocal tracts have physical properties (i.e., articulatory motions) differing from those of infants' vocal tracts. To solve this problem, a model based on the motor theory of speech perception, was constructed. This model suggests that infants simulate the speech generation by estimating their own articulatory motions in order to interpret the speech sounds of adults. Applying this model enables the vocal imitation system to estimate articulatory motions for unexperienced speech sounds that have not actually been generated by the system. The system was implemented by using Recurrent Neural Network with Parametric Bias (RNNPB) and a physical vocal tract model, called the Maeda model. Experimental results demonstrated that the system was sufficiently robust with respect to individual differences in speech sounds and could imitate unexperienced vowel sounds.

UR - http://www.scopus.com/inward/record.url?scp=51349149903&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51349149903&partnerID=8YFLogxK

U2 - 10.1109/IROS.2007.4399137

DO - 10.1109/IROS.2007.4399137

M3 - Conference contribution

AN - SCOPUS:51349149903

SN - 1424409128

SN - 9781424409129

SP - 1846

EP - 1851

BT - IEEE International Conference on Intelligent Robots and Systems

ER -