Comparing In-ear EOG for Eye-Movement Estimation With Eye-Tracking: Accuracy, Calibration, and Speech Comprehension

Abstract

This presentation details and evaluates a method for estimating the attended speaker during a two-person conversation by means of in-ear electro-oculography (EOG). Twenty-five hearing-impaired participants were fitted with molds equipped with EOG electrodes (in-ear EOG) and wore eye-tracking glasses while watching a video of two life-size people in a dialog solving a Diapix task. The dialogue was directionally presented and together with background noise in the frontal hemisphere at 60 dB SPL. During three conditions of steering (none, in-ear EOG, conventional eye-tracking), participants' comprehension was periodically measured using multiple-choice questions. Based on eye movement detection by in-ear EOG or conventional eye-tracking, the estimated attended speaker was amplified by 6 dB. In the in-ear EOG condition, the estimate was based on one selected channel pair of electrodes out of 36 possible electrodes. A novel calibration procedure introducing three different metrics was used to select the measurement channel. The in-ear EOG attended speaker estimates were compared to those of the eye-tracker. Across participants, the mean accuracy of in-ear EOG estimation of the attended speaker was 68%, ranging from 50 to 89%. Based on offline simulation, it was established that higher scoring metrics obtained for a channel with the calibration procedure were significantly associated with better data quality. Results showed a statistically significant improvement in comprehension of about 10% in both steering conditions relative to the no-steering condition. Comprehension in the two steering conditions was not significantly different. Further, better comprehension obtained under the in-ear EOG condition was significantly correlated with more accurate estimation of the attended speaker. In conclusion, this study shows promising results in the use of in-ear EOG for visual attention estimation with potential for applicability in hearing assistive devices.

Multilevel Modelling of Gaze from Hearing-impaired Listeners following a Realistic Conversation

“…The audio for each loudspeaker was equalized with a finite-impulse response filter based on the inverse of the loudspeakers’ 3 rd -octave smoothed frequency response function, measured at the center-of-head position. Furthermore, the signal loudness was modified for each participant individually to compensate for their hearing loss in their better ear (Moore & Glasberg, 1998; Skoglund et al, 2022).…”

“…They were regular users of hearing aids. All were native Danish speakers with no prior experience with the testing materials, and reported that they could see the stimuli clearly at 1.5 metres distance without the use of glasses or contact lenses (Skoglund et al, 2022).…”

“…Furthermore, the signal loudness was modified for each participant individually to compensate for their hearing loss in their better ear (Moore & Glasberg, 1998;Skoglund et al, 2022).…”

“…All authors are employed by Oticon A/S (Smørum, Denmark). The authors would like to acknowledge Martin Andersen and Mike Lind Rank (T&W Engineering A/S, Allerød, Denmark) for their contributions to the experiment from which we resourced the data of the current investigation (Skoglund et al, 2022).…”

“…In the past fifteen years, eye-gaze has also become a topic of interest in the field of hearing science due to its potential application as a signal for controlling hearing aid technology (e.g. Best et al, 2017; Favre-Félix et al, 2018; Hart et al, 2009; Hládek et al, 2019; Kidd, 2017; Roverud et al, 2017; Skoglund et al, 2022). Most recently, researchers have started studying eye-gaze to describe the behavior of hearing-impaired people in realistic multitalker situations (Hadley et al, 2019; Hendrikse & Llorach, 2019; Lu et al, 2021), an application that capitalizes on our innate tendency to look at the targets of our attention and our attraction towards social stimuli.…”