Classification of Sound Environments for Hearing Aid Applications

Christine Oldenborg Voetmann

AbstractThe goal of this project is to create a Matlab based framework for sound environment classification including an investigation of the most robust features for classification of various sound environments. Hearing aids use different amplification strategies targeted at different situations/ sound environments. The different amplification strategies are normally chosen by the user with a remote control or via a program switch mounted on the hearing aid. Modern hearing aids contain various detectors which are used to automatically change a number of parameters of the hearing aid. The detectors are typically not fully descriptive for the sound environment. This project is seeking to improve the classification of the various sound environments relevant for the hearing aid user and focus is on two classes; car environment against miscellaneous environments. The final framework is build up by a number of sound files covering the different sound environments, a list of features is configured from the openSMILE toolkit [12] and a classification tree is used as the classifying algorithm. By using the build robust framework a sensitivity of 91:6%  4:69% and a specificity of 96:44%3:13% is achieved, but an expansion of the framework is recommended before an implementation in a hearing aid.
TypeMaster's thesis [Academic thesis]
PublisherTechnical University of Denmark, DTU Informatics, E-mail:
AddressAsmussens Alle, Building 305, DK-2800 Kgs. Lyngby, Denmark
NoteSupervised by Associate Professor Jan Larsen,, DTU Informatics
Electronic version(s)[pdf]
Publication link
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing

Back  ::  IMM Publications