Objective Speech Quality Estimation of In-Ear Microphone Speech

Speech captured from an in-ear microphone (IEM) under an intra-aural device is beneficial in extremely noisy environments as it maintains a relatively high signal to noise ratio. Due to its limited bandwidth, speech enhancement is required in order to obtain a more natural speech. Consequently, quick and practical measurement of speech quality is important. In this paper, we compare the performance of the quality of intrusive and non-intrusive objective quality metrics on IEM speech, and propose an adaptation of a non-intrusive metric, the speech-toreverberation modulation energy ratio (SRMR) to IEM speech signals. Changes are implemented to take into account the effect of the occluded ear on the recorded speech signals, which causes an amplification in the bone conduction sounds in the ear canal. We show that the updated SRMR metric, SRMRIEM, significantly reduces the performance gap between nonintrusive and intrusive metrics.