The aim of the research work presented is an automatic singing voice quality/type recognition system. For this purpose a database containing singers’ sample recordings is constructed and parameters are extracted from recorded voices of trained and untrained singers of different voice types. Parameters, which are especially designed for the analysis of the singing voice, are analyzed and a feature vector is formed. Each of singers’ voice samples is judged by experts and information about voice type/quality is obtained. Parameters extracted are used in the training process of a neural network and the effectiveness of an automatic voice timbre/quality classification is tested by comparing automatic recognition results with subjective expert judgements. Finally, discussion of results is presented and conclusions are derived.
Affiliation: Gdansk University of Technology
AES Convention: 121 (October 2006) Paper Number: 6898
Publication Date: October 1, 2006
Subject: Analysis and Synthesis
No AES members have commented on this paper yet.
If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.