14thAnnual Conference of the International Speech Communication Association

Lyon, France
August 25-29, 2013

Predicting the Bilateral Advantage in Cochlear Implantees Using a Non-Intrusive Speech Intelligibility Measure

Stefano Cosentino (1), Tiago H. Falk (2), David McAlpine (1)

(1) University College London, UK
(2) INRS-EMT, Canada

A measure to predict speech intelligibility in unilateral and bilateral cochlear implant (CI) users is proposed that does not need a priori information (i.e. is non-intrusive), such as the room acoustics. Such measure, termed BiSIMCI, combines an equalization-cancellation stage together with a modulation frequency estimation stage. Simulated and actual subjective data from CI users were used to validate the proposed measure. The actual CI subjective data consisted of speech reception thresholds (SRTs) collected in anechoic rooms with a total of 28 target/interferer spatial configurations. The simulated CI subjective data were generated by running the intrusive algorithm by Culling et al. [Ear & Hearing 33 (6), 673.682 (2012)] across 109 different target/interferer conditions from two environments, one anechoic and one highly reverberant room (RT60 = 0.89s). The experimental results indicate that the proposed nonintrusive measure provides reliable predictions when compared with both actual and simulated SRT; an average correlation of 0.94 was reported for these conditions, and an average correlation of 0.97 was obtained when some intrusive assumptions were made.

Full Paper

Bibliographic reference.  Cosentino, Stefano / Falk, Tiago H. / McAlpine, David (2013): "Predicting the bilateral advantage in cochlear implantees using a non-intrusive speech intelligibility measure", In INTERSPEECH-2013, 2277-2281.