Boosting scores fusion approach using Front-End Diversity and adaboost Algorithm, for speaker verification

A new speech feature extraction method called Mel Modified Group Delay coefficients (MMGDCs) is presented in this paper. In this method, the modified group delay spectrum detects the high formants frequencies, while the Mel filters select these desired formants in the high frequency regions. Also in this paper, a scores fusion approach is proposed between MMGDCs, Mel coefficients (MFCCs) and their extensions using the asymmetric tappers. The adaboost algorithm is used as strategy of this fusion. The performances evaluation of the proposed features and their extended variants are carried out on NIST 2000 corpus, and tested in both clean and simulated noisy conditions, using different noise categories extracted from the NOISEX-92 database. The obtained results show the superiority of the proposed MMGDCs against MFCCs in terms of error reduction, and the power of adaboost algorithm to make the fusion between MMGDCs and MFCCs better, especially under noisy environments.