Speaker localization using the TDOA-based feature matrix for a humanoid robot

Ui Hyun Kim, Jinsung Kim, Doik Kim, Hyogon Kim, Bum Jae You

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

14 Citations (Scopus)

Abstract

Research on human-robot interaction has recently been getting increasing attention. In the research field of human-robot interaction, speech signal processing in particular is the source of much interest. In this paper, we report on a speaker localization system with six microphones for a humanoid robot called MAHRU of KIST and propose a time delay of arrival (TDOA)-based feature matrix with its algorithm based on the minimum sum of absolute errors (MSAE) for sound source localization. The TDOA-based feature matrix is defined as a simple database matrix calculated from pairs of microphones installed on a humanoid robot. To verify the solid performance of our speaker localization system for a humanoid robot, we present the various experimental results for the speech sources at all directions within S m distance and the height divided into three parts.

Original languageEnglish
Title of host publicationProceedings of the 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN
Pages610-615
Number of pages6
DOIs
Publication statusPublished - 2008 Oct 6
Event17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN - Munich, Germany
Duration: 2008 Aug 12008 Aug 3

Other

Other17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN
CountryGermany
CityMunich
Period08/8/108/8/3

Fingerprint

Time delay
Human robot interaction
Robots
Microphones
Signal processing
Acoustic waves

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction

Cite this

Kim, U. H., Kim, J., Kim, D., Kim, H., & You, B. J. (2008). Speaker localization using the TDOA-based feature matrix for a humanoid robot. In Proceedings of the 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN (pp. 610-615). [4600734] https://doi.org/10.1109/ROMAN.2008.4600734

Speaker localization using the TDOA-based feature matrix for a humanoid robot. / Kim, Ui Hyun; Kim, Jinsung; Kim, Doik; Kim, Hyogon; You, Bum Jae.

Proceedings of the 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN. 2008. p. 610-615 4600734.

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

Kim, UH, Kim, J, Kim, D, Kim, H & You, BJ 2008, Speaker localization using the TDOA-based feature matrix for a humanoid robot. in Proceedings of the 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN., 4600734, pp. 610-615, 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN, Munich, Germany, 08/8/1. https://doi.org/10.1109/ROMAN.2008.4600734
Kim UH, Kim J, Kim D, Kim H, You BJ. Speaker localization using the TDOA-based feature matrix for a humanoid robot. In Proceedings of the 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN. 2008. p. 610-615. 4600734 https://doi.org/10.1109/ROMAN.2008.4600734
Kim, Ui Hyun ; Kim, Jinsung ; Kim, Doik ; Kim, Hyogon ; You, Bum Jae. / Speaker localization using the TDOA-based feature matrix for a humanoid robot. Proceedings of the 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN. 2008. pp. 610-615
@inproceedings{0dccebfee2794233970aa79a96c73343,
title = "Speaker localization using the TDOA-based feature matrix for a humanoid robot",
abstract = "Research on human-robot interaction has recently been getting increasing attention. In the research field of human-robot interaction, speech signal processing in particular is the source of much interest. In this paper, we report on a speaker localization system with six microphones for a humanoid robot called MAHRU of KIST and propose a time delay of arrival (TDOA)-based feature matrix with its algorithm based on the minimum sum of absolute errors (MSAE) for sound source localization. The TDOA-based feature matrix is defined as a simple database matrix calculated from pairs of microphones installed on a humanoid robot. To verify the solid performance of our speaker localization system for a humanoid robot, we present the various experimental results for the speech sources at all directions within S m distance and the height divided into three parts.",
author = "Kim, {Ui Hyun} and Jinsung Kim and Doik Kim and Hyogon Kim and You, {Bum Jae}",
year = "2008",
month = "10",
day = "6",
doi = "10.1109/ROMAN.2008.4600734",
language = "English",
isbn = "9781424422135",
pages = "610--615",
booktitle = "Proceedings of the 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN",

}

TY - GEN

T1 - Speaker localization using the TDOA-based feature matrix for a humanoid robot

AU - Kim, Ui Hyun

AU - Kim, Jinsung

AU - Kim, Doik

AU - Kim, Hyogon

AU - You, Bum Jae

PY - 2008/10/6

Y1 - 2008/10/6

N2 - Research on human-robot interaction has recently been getting increasing attention. In the research field of human-robot interaction, speech signal processing in particular is the source of much interest. In this paper, we report on a speaker localization system with six microphones for a humanoid robot called MAHRU of KIST and propose a time delay of arrival (TDOA)-based feature matrix with its algorithm based on the minimum sum of absolute errors (MSAE) for sound source localization. The TDOA-based feature matrix is defined as a simple database matrix calculated from pairs of microphones installed on a humanoid robot. To verify the solid performance of our speaker localization system for a humanoid robot, we present the various experimental results for the speech sources at all directions within S m distance and the height divided into three parts.

AB - Research on human-robot interaction has recently been getting increasing attention. In the research field of human-robot interaction, speech signal processing in particular is the source of much interest. In this paper, we report on a speaker localization system with six microphones for a humanoid robot called MAHRU of KIST and propose a time delay of arrival (TDOA)-based feature matrix with its algorithm based on the minimum sum of absolute errors (MSAE) for sound source localization. The TDOA-based feature matrix is defined as a simple database matrix calculated from pairs of microphones installed on a humanoid robot. To verify the solid performance of our speaker localization system for a humanoid robot, we present the various experimental results for the speech sources at all directions within S m distance and the height divided into three parts.

UR - http://www.scopus.com/inward/record.url?scp=52949109221&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=52949109221&partnerID=8YFLogxK

U2 - 10.1109/ROMAN.2008.4600734

DO - 10.1109/ROMAN.2008.4600734

M3 - Conference contribution

SN - 9781424422135

SP - 610

EP - 615

BT - Proceedings of the 17th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN

ER -