2026-04-17T05:50:44Zhttps://recercat.cat/oai/request

oai:recercat.cat:10230/308252025-12-21T18:05:29Zcom_2072_6col_2072_452952

00925njm 22002777a 4500 dc Farrús, Mireia author Ejarque, Pascual author Temko, Andrey author Hernando, Javier author 2017-04-18T08:23:54Z 2017-04-18T08:23:54Z 2007 Comunicació presentada a la International Conference on Biometrics (ICB) celebrada a Seoul (Korea) els dies 27 a 29 d'agost de 2007. It has been shown that prosody helps to improve voice spectrum based speaker recognition systems. Therefore, prosodic features can also be used in multimodal person verification in order to achieve better results. In this paper, a multimodal recognition system based on facial and vocal tract spectral features is improved by adding prosodic information. Matcher weighting method and support vector machines have been used as fusion techniques, and histogram equalization has been applied before SVM fusion as a normalization technique. The results show that the performance of a SVM multimodal verification system can be improved by using histogram equalization, especially when the equalization is applied to those scores giving the highest EER values. Speaker recognition Multimodality Fusion Support vector machines Histogram equalization Prosody Voice spectrum Face Histogram equalization in SVM multimodal person verification