Data-driven approach for auditory profiling

Activity: Talks and presentationsConference presentations

View graph of relations

Raul Sanchez Lopez - Guest lecturer

Federica Bianchi - Guest lecturer

Michal Fereczkowski - Guest lecturer

Sébastien Santurette - Guest lecturer

Torsten Dau - Guest lecturer

Nowadays, the pure-tone audiogram is the main tool used to characterize hearing loss and to fit
hearing aids. However, the perceptual consequences of hearing loss are typically associated not only with a loss of sensitivity, but also with a clarity loss that is not captured by the audiogram. Detailed characterization of hearing loss has to be simplified to efficiently investigate the specific compensation needs of individual listeners. We hypothesized that any listeners' hearing can be characterized along two dimensions of distortion: type I and type II. While type I can be linked
to factors affecting audibility, type II reflects non-audibility-related distortions. To test our hypothesis, the individual performance data from two previous studies was re-analyzed using archetypal analysis. Unsupervised learning was used to identify extreme patterns in the data which form the basis for different auditory profiles.
Next, a decision tree was determined to classify the listeners into one of the profiles. The new analysis provides evidence for the existence of four profiles in the data. The most significant predictors for profile identification were related to binaural processing, auditory non-linearity, and speech perception. The current approach is promising for analyzing other existing data sets in order to select the most relevant tests for auditory profiling.
23 Aug 201725 Aug 2017

Conference

TitleInternational Symposium on Auditory and Audiological Research
Abbreviated titleISAAR 2017
Date23/08/201725/08/2017
Website
LocationHotel Nyborg Strand
CityNyborg
CountryDenmark

    Keywords

  • hearing deficits
Download as:
Download as PDF
Select render style:
ShortLong
PDF
Download as HTML
Select render style:
ShortLong
HTML
Download as Word
Select render style:
ShortLong
Word

ID: 136745360