In this paper we study the suitability and performance of four major speech denoising algorithms as GCC weighting functions and discuss the role of the microphones' frequency response on the localization estimates. An evaluation is made with the humanoid robot Nao. Moving away from simulated environments, we look at the performance of sound source localization under different in-system and ambient noise conditions. We also present a TDOA/GCC based sound source localization method for real-world humanoid robots which was used for our experiments. This method addresses the robot's shape influence by utilizing a pre-measured set of TDOAs.
Original languageEnglish
Title of host publicationProceedings of the 11th International Conference on Information Sciences, Signal Processing and their Applications (ISSPA 2012)
PublisherIEEE
Pages369-374
Number of pages6
ISBN (Electronic)978-1-4673-0382-8, 978-1-4673-0380-4
ISBN (Print)978-1-4673-0381-1
DOIs
Publication statusPublished - Jul 2012
Event11th International Conference on Information Sciences, Signal Processing and their Applications (ISSPA 2012) - Montreal, Canada
Duration: 2 Jul 20125 Jul 2012
http://www.synchromedia.ca/isspa2012/

Conference

Conference11th International Conference on Information Sciences, Signal Processing and their Applications (ISSPA 2012)
CountryCanada
CityMontreal
Period2/07/125/07/12
Internet address

    Research areas

  • microphone arrays, sound source localization, time delay of arrival (TDOA), generalized cross correlation (GCC), speech denoising, Nao

ID: 2156855