Robust statistical-based speaker's location detection algorithm in a vehicular environment

Abstract

This work proposes a threshold adaptation method to detect speaker's location in a vehicular environment. The method is robust to unmodeled sound source locations in a noisy environment and uses a single linear microphone array. The proposed approach is an improvement over previous work [12] which adopts Gaussian mixture models (GMMs) to model location-dependent but content and speaker independent acoustic characteristics of sound sources. Experimental results show that this scheme can overcome the far-filed and near-riled problem with the same architecture and perform well in both line-of-sight and non-line-of-sight cases.