Autonomous voice acquisition of a talking robot based on topological structure learning by applying dual-SOM

Mitsuki Kitani, Tatsuya Hara, Hideyuki Sawada

研究成果: Article

抄録

This paper presents the method of autonomous voice acquisition for a talking robot by applying a dual-SOM. We have so far developed the talking robot, which has mechanical organs as a human. By applying an auditory feedback control, the robot autonomously learns the vocalization skill. For the autonomous learning method, a Self Organizing Neural Network (SONN) by combining a Self-Organizing Map (SOM) with a Neural Network (NN) was employed. The SONN had 2-dimensional mapping space, which was used to locate phonetic features of voices generated by the robot. By choosing cells on the map, voice articulations were autonomously recreated. However, due to the spatial restriction of the map, the voice transition from one vocal sound to another was not always recreated properly. To solve the problems, a dual-SOM, the combination of a phonetic-SOM and a motor-SOM, both of which have 3 dimensional mapping spaces, is introduced. The structure of the dual-SOM is firstly described, and then acquired vocal sounds are evaluated, together with the analysis of the behavior of the SOM.

元の言語English
ページ(範囲)1062-1070
ページ数9
ジャーナルNihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C
77
発行部数775
出版物ステータスPublished - 2011
外部発表Yes

Fingerprint

Self organizing maps
Robots
Speech analysis
Neural networks
Acoustic waves
Feedback control

ASJC Scopus subject areas

  • Mechanical Engineering
  • Mechanics of Materials
  • Industrial and Manufacturing Engineering

これを引用

@article{411f39997a5146df820568e6989ee187,
title = "Autonomous voice acquisition of a talking robot based on topological structure learning by applying dual-SOM",
abstract = "This paper presents the method of autonomous voice acquisition for a talking robot by applying a dual-SOM. We have so far developed the talking robot, which has mechanical organs as a human. By applying an auditory feedback control, the robot autonomously learns the vocalization skill. For the autonomous learning method, a Self Organizing Neural Network (SONN) by combining a Self-Organizing Map (SOM) with a Neural Network (NN) was employed. The SONN had 2-dimensional mapping space, which was used to locate phonetic features of voices generated by the robot. By choosing cells on the map, voice articulations were autonomously recreated. However, due to the spatial restriction of the map, the voice transition from one vocal sound to another was not always recreated properly. To solve the problems, a dual-SOM, the combination of a phonetic-SOM and a motor-SOM, both of which have 3 dimensional mapping spaces, is introduced. The structure of the dual-SOM is firstly described, and then acquired vocal sounds are evaluated, together with the analysis of the behavior of the SOM.",
keywords = "3 Dimentional Self-Organizing Map, Adaptive Learning, Talking Robot",
author = "Mitsuki Kitani and Tatsuya Hara and Hideyuki Sawada",
year = "2011",
language = "English",
volume = "77",
pages = "1062--1070",
journal = "Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C",
issn = "0387-5024",
publisher = "Japan Society of Mechanical Engineers",
number = "775",

}

TY - JOUR

T1 - Autonomous voice acquisition of a talking robot based on topological structure learning by applying dual-SOM

AU - Kitani, Mitsuki

AU - Hara, Tatsuya

AU - Sawada, Hideyuki

PY - 2011

Y1 - 2011

N2 - This paper presents the method of autonomous voice acquisition for a talking robot by applying a dual-SOM. We have so far developed the talking robot, which has mechanical organs as a human. By applying an auditory feedback control, the robot autonomously learns the vocalization skill. For the autonomous learning method, a Self Organizing Neural Network (SONN) by combining a Self-Organizing Map (SOM) with a Neural Network (NN) was employed. The SONN had 2-dimensional mapping space, which was used to locate phonetic features of voices generated by the robot. By choosing cells on the map, voice articulations were autonomously recreated. However, due to the spatial restriction of the map, the voice transition from one vocal sound to another was not always recreated properly. To solve the problems, a dual-SOM, the combination of a phonetic-SOM and a motor-SOM, both of which have 3 dimensional mapping spaces, is introduced. The structure of the dual-SOM is firstly described, and then acquired vocal sounds are evaluated, together with the analysis of the behavior of the SOM.

AB - This paper presents the method of autonomous voice acquisition for a talking robot by applying a dual-SOM. We have so far developed the talking robot, which has mechanical organs as a human. By applying an auditory feedback control, the robot autonomously learns the vocalization skill. For the autonomous learning method, a Self Organizing Neural Network (SONN) by combining a Self-Organizing Map (SOM) with a Neural Network (NN) was employed. The SONN had 2-dimensional mapping space, which was used to locate phonetic features of voices generated by the robot. By choosing cells on the map, voice articulations were autonomously recreated. However, due to the spatial restriction of the map, the voice transition from one vocal sound to another was not always recreated properly. To solve the problems, a dual-SOM, the combination of a phonetic-SOM and a motor-SOM, both of which have 3 dimensional mapping spaces, is introduced. The structure of the dual-SOM is firstly described, and then acquired vocal sounds are evaluated, together with the analysis of the behavior of the SOM.

KW - 3 Dimentional Self-Organizing Map

KW - Adaptive Learning

KW - Talking Robot

UR - http://www.scopus.com/inward/record.url?scp=84856435804&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856435804&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84856435804

VL - 77

SP - 1062

EP - 1070

JO - Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C

JF - Nihon Kikai Gakkai Ronbunshu, C Hen/Transactions of the Japan Society of Mechanical Engineers, Part C

SN - 0387-5024

IS - 775

ER -