Speaker localization in a reverberant environment using spherical statistical modeling Academic Article uri icon

abstract

  • Estimation of the direction of arrival (DoA) of speakers in reverberant environments is an important audio signal processing task in a wide range of applications. Recently, a reverberation-robust method for DoA estimation has been developed. It is based on the identification of time-frequency bins that are dominated by the direct path from the source. As the DoA statistics was found to have a multimodal distribution, clustering using Gaussian mixture modeling improved localization accuracy. However, this method employed linear statistics over the azimuth and elevation angles, therefore introducing between 0 and 360 degrees azimuth. This work explores the use of spherical statistics in the direct-path dominance approach to speaker localization in reverberant rooms, providing a more suitable angular representation. Theoretical and experimental aspects of the proposed approach are investigated and validated using a computer simulation of a speaker in a room.

publication date

  • January 1, 2017