“…One of their important contributions is that the weighted cluster coefficients are integrated so that their model can infer the weighted contribution at the prediction stage. Nagaraja and Jayanna [33] propose a new approach combining Gaussian mixture model-universal background model (GMM-UBM) and learning vector quantization (LVQ)-based classifiers for monolingual and cross-lingual speaker identification using multi-taper mel-frequency cepstral coefficient (MFCC) features. The results show that their proposed combination system can be used to improve the multilingual speaker identification process.…”