A Robust Statistical-Based Speaker's Location Detection Algorithm in a Vehicular Environment

Abstract

This work presents a robust speaker's location detection algorithm using a single linear microphone array that is capable of detecting multiple speech sources under the assumption that there exist nonoverlapped speech segments among sources. Namely, the overlapped speech segments are treated as uncertainty and are not used for detection. The location detection algorithm is derived from a previous work (2006), where Gaussian mixture models (GMMs) are used to model location-dependent and content and speaker-independent phase difference distributions. The proposed algorithm is proven to be robust against the complex vehicular acoustics including noise, reverberation, near-filed, far-field, line-of-sight, and non-line-of-sight conditions, and microphones' mismatch. An adaptive system architecture is developed to adjust the Gaussian mixture (GM) location model to environmental noises. To deal with unmodeled speech sources as well as overlapped speech signals, a threshold adaptation scheme is proposed in this work. Experimental results demonstrate high detection accuracy in a noisy vehicular environment.

Detecting driver phone use leveraging car speakers

“…Toward speaker localization for in-car environment, both Swerdlow [12] and Hu [24] proposed to detect the speaker's location inside a car using the microphone array. RodriguezAscariz et al [33] developed a system for detecting driver use of mobile phones using specialized rectenna.…”

Sensing Driver Phone Use with Acoustic Ranging through Car Speakers

“…Toward speaker localization for in-car environment, both Swerdlow et al [12] and Hu et al [25] proposed to detect the speaker's location inside a car using the microphone array. Rodriguez-Ascariz et al [36] developed a system for detecting driver use of mobile phones using specialized rectenna.…”

Supervised audio source localisation using microphone array

“…To increase the information of the frenqency amplitude ratio, the distance between our microphones is higher than 90 cm. When the audio source location is known, it is possible to synchronize both signal received by a microphone pair to take into account of the phase information on a large frequency band: (5) with Tan = i5,;;n , where ban is the distance between the position a and the microphone n.…”

“…For many years, the re searchers have proposed systems based on microphone ar ray that use DOA, TDOA principles [1,2,3,4] or phases differences feature [5] . In [6,7], the authors propose to use two microphones and the specific acoustical cues, ILD (interaural level difference) and lTD (interaural time dif ference).…”

“…In [6,7], the authors propose to use two microphones and the specific acoustical cues, ILD (interaural level difference) and lTD (interaural time dif ference). However, in all previous papers, microphones are placed in front of the speaker and the auhors do not take into account a large variability of the direction of the speaker except for [8,5,7]. Our work is inspired from [7] .…”