Robust speaker's location estimation in a vehicle environment using GMM models

Wei Han Liu, Chieh Cheng Cheng, Jwu-Sheng Hu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


In this work, a robust speaker's location estimation method in a vehicle environment is presented. This method applies Gaussian mixture models (GMM) to the phase information obtained from a microphone array. The individual Gaussian component of a GMM represents some general location-dependent phase difference distribution between two microphones. These distributions are effective in modeling the speaker's location. The relation between geometry of microphone array and frequency band is taken into consideration to avoid aliasing problems. The proposed approach provides an accurate estimation even in near-field, noisy and complex vehicle environment. Moreover, it performs well not only in non-line-of-sight cases, but also in the conditions that the speakers are aligned in a direction to the microphone array with difference distances. Experiments are conducted in a mini-van vehicle and the results show that the proposed method outperform the popular technique multiple signal classification method (MUSIC) in different SNR cases.

Original languageEnglish
Title of host publication2005 IEEE Intelligent Vehicles Symposium, Proceedings
Number of pages6
StatePublished - 1 Dec 2005
Event2005 IEEE Intelligent Vehicles Symposium - Las Vegas, NV, United States
Duration: 6 Jun 20058 Jun 2005

Publication series

NameIEEE Intelligent Vehicles Symposium, Proceedings


Conference2005 IEEE Intelligent Vehicles Symposium
CountryUnited States
CityLas Vegas, NV


  • DOA
  • GMM
  • Microphone array

Fingerprint Dive into the research topics of 'Robust speaker's location estimation in a vehicle environment using GMM models'. Together they form a unique fingerprint.

Cite this