In the therapy of the hearing impaired one of the key problems is how
to deal with the lack of proper auditive feedback which impedes the
development of intelligible speech. The effectiveness of the therapy
relies heavily on accurate phoneme recognition [,,]. Because of the
environmental difficulties, simple recognition algorithms may have a
weak classification performance, so various techniques such as normalization
and classifier combination are applied to increase the recognition accuracy.
This paper examines Vocal Tract Length Normalization techniques [,]
focusing mainly on the real-time parameter estimation [], and the majority
of classifier combination schemes, including the traditional ( Prod,
Sum, Min, Max) [], basic linear (simple,
weighted, AHP-based [] averaging), and some
special linear (Bagging, Boosting) combinations.
Based on the results we conclude that hybrid combinations can improve
the effectiveness of the real-time normalization methods.
