Enhancement of Speech/Music Classification for 3GPP2 SMV Codec Employing Discriminative Weight Training
Sang-Ick Kang, Joon‐Hyuk Chang, Seong-Ro Lee · The Journal of the Acoustical Society of Korea · 2008
In this paper, we propose a novel approach to improve the performance of speech/music classification for the selectable mode vocoder (SMV) of 3GPP2 using the discriminative weight training which is based on the minimum classification error (MCE) algorithm. We first present an effective analysis of the features and the classification method adopted in the conventional SMV. And then proposed the speech/music decision rule is expressed as the geometric mean of optimally weighted features which are selected from the SMV. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional scheme of the SMV.