Voice articulatory training with a talking robot for the auditory impaired

Mitsuki Kitani, Tatusya Hara, Hideyuki Sawada

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The authors have developed a vocalization training system for the auditory impaired using a talking robot. The training system mainly consists of a talking robot that has mechanical organs like a human. With an adaptive learning strategy using an auditory feedback control, the robot autonomously learns the vocalization, and then reproduces the speech articulation from inputted sounds. In the previous system, the speech-learning algorithm of the robot was constructed by employing a self-organizing neural network (SONN), which consists of the combination of a self-organizing map (SOM) and a neural network (NN). However, improper maps were occasionally generated in the results of the speech articulation learning. To solve this problem, a new algorithm introducing two three-dimensional SOMs, called a dual-SOM, was employed for the autonomous learning of the robotic articulations. By applying the robot and its properties, we have constructed an interactive training system. The training is divided into two approaches; one is to use the talking robot to show the shape and the motion of the vocal organs, and the other is to use a topological map to present the difference of phonetic features of a trainee's voices. In this study, first, the construction of the training system is described together with the autonomous learning of robotic vocalization using the dual-SOM algorithm, and then the analysis of the speech training progress is presented based on the phonetic features and the mechanical vocal articulations.

Original languageEnglish
Pages (from-to)63-67
Number of pages5
JournalInternational Journal on Disability and Human Development
Volume10
Issue number1
DOIs
Publication statusPublished - 2011 Mar
Externally publishedYes

Fingerprint

Voice Training
Learning
Phonetics
Robotics

Keywords

  • Adaptive learning
  • Interactive speech training system
  • Talking robot

ASJC Scopus subject areas

  • Rehabilitation
  • Geriatrics and Gerontology
  • Advanced and Specialised Nursing
  • Psychiatry and Mental health
  • Sensory Systems
  • Speech and Hearing

Cite this

Voice articulatory training with a talking robot for the auditory impaired. / Kitani, Mitsuki; Hara, Tatusya; Sawada, Hideyuki.

In: International Journal on Disability and Human Development, Vol. 10, No. 1, 03.2011, p. 63-67.

Research output: Contribution to journalArticle

@article{b6108c0ad7624742851e022eb3e75bd3,
title = "Voice articulatory training with a talking robot for the auditory impaired",
abstract = "The authors have developed a vocalization training system for the auditory impaired using a talking robot. The training system mainly consists of a talking robot that has mechanical organs like a human. With an adaptive learning strategy using an auditory feedback control, the robot autonomously learns the vocalization, and then reproduces the speech articulation from inputted sounds. In the previous system, the speech-learning algorithm of the robot was constructed by employing a self-organizing neural network (SONN), which consists of the combination of a self-organizing map (SOM) and a neural network (NN). However, improper maps were occasionally generated in the results of the speech articulation learning. To solve this problem, a new algorithm introducing two three-dimensional SOMs, called a dual-SOM, was employed for the autonomous learning of the robotic articulations. By applying the robot and its properties, we have constructed an interactive training system. The training is divided into two approaches; one is to use the talking robot to show the shape and the motion of the vocal organs, and the other is to use a topological map to present the difference of phonetic features of a trainee's voices. In this study, first, the construction of the training system is described together with the autonomous learning of robotic vocalization using the dual-SOM algorithm, and then the analysis of the speech training progress is presented based on the phonetic features and the mechanical vocal articulations.",
keywords = "Adaptive learning, Interactive speech training system, Talking robot",
author = "Mitsuki Kitani and Tatusya Hara and Hideyuki Sawada",
year = "2011",
month = "3",
doi = "10.1515/IJDHD.2011.012",
language = "English",
volume = "10",
pages = "63--67",
journal = "International Journal on Disability and Human Development",
issn = "2191-1231",
publisher = "Freund Publishing House Ltd",
number = "1",

}

TY - JOUR

T1 - Voice articulatory training with a talking robot for the auditory impaired

AU - Kitani, Mitsuki

AU - Hara, Tatusya

AU - Sawada, Hideyuki

PY - 2011/3

Y1 - 2011/3

N2 - The authors have developed a vocalization training system for the auditory impaired using a talking robot. The training system mainly consists of a talking robot that has mechanical organs like a human. With an adaptive learning strategy using an auditory feedback control, the robot autonomously learns the vocalization, and then reproduces the speech articulation from inputted sounds. In the previous system, the speech-learning algorithm of the robot was constructed by employing a self-organizing neural network (SONN), which consists of the combination of a self-organizing map (SOM) and a neural network (NN). However, improper maps were occasionally generated in the results of the speech articulation learning. To solve this problem, a new algorithm introducing two three-dimensional SOMs, called a dual-SOM, was employed for the autonomous learning of the robotic articulations. By applying the robot and its properties, we have constructed an interactive training system. The training is divided into two approaches; one is to use the talking robot to show the shape and the motion of the vocal organs, and the other is to use a topological map to present the difference of phonetic features of a trainee's voices. In this study, first, the construction of the training system is described together with the autonomous learning of robotic vocalization using the dual-SOM algorithm, and then the analysis of the speech training progress is presented based on the phonetic features and the mechanical vocal articulations.

AB - The authors have developed a vocalization training system for the auditory impaired using a talking robot. The training system mainly consists of a talking robot that has mechanical organs like a human. With an adaptive learning strategy using an auditory feedback control, the robot autonomously learns the vocalization, and then reproduces the speech articulation from inputted sounds. In the previous system, the speech-learning algorithm of the robot was constructed by employing a self-organizing neural network (SONN), which consists of the combination of a self-organizing map (SOM) and a neural network (NN). However, improper maps were occasionally generated in the results of the speech articulation learning. To solve this problem, a new algorithm introducing two three-dimensional SOMs, called a dual-SOM, was employed for the autonomous learning of the robotic articulations. By applying the robot and its properties, we have constructed an interactive training system. The training is divided into two approaches; one is to use the talking robot to show the shape and the motion of the vocal organs, and the other is to use a topological map to present the difference of phonetic features of a trainee's voices. In this study, first, the construction of the training system is described together with the autonomous learning of robotic vocalization using the dual-SOM algorithm, and then the analysis of the speech training progress is presented based on the phonetic features and the mechanical vocal articulations.

KW - Adaptive learning

KW - Interactive speech training system

KW - Talking robot

UR - http://www.scopus.com/inward/record.url?scp=84871404718&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871404718&partnerID=8YFLogxK

U2 - 10.1515/IJDHD.2011.012

DO - 10.1515/IJDHD.2011.012

M3 - Article

AN - SCOPUS:84871404718

VL - 10

SP - 63

EP - 67

JO - International Journal on Disability and Human Development

JF - International Journal on Disability and Human Development

SN - 2191-1231

IS - 1

ER -