Speaker verification under mismatched data conditions
This study presents investigations into the effectiveness of the state-of-the-art speaker verification techniques (i.e. GMM-UBM and GMM-SVM) in mismatched noise conditions. Based on experiments using white and real world noise, it is shown that the verification performance offered by these methods is severely affected when the level of degradation in the test material is different from that in the training utterances. To address this problem, a modified realisation of the parallel model combination (PMC) method is introduced and a new form of test normalisation (T-norm), termed condition adjusted T-norm, is proposed. It is experimentally demonstrated that the use of these techniques with GMM-UBM can significantly enhance the accuracy in mismatched noise conditions. Based on the experimental results, it is observed that the resultant relative improvement achieved for GMM-UBM (under the most severe mismatch condition considered) is in excess of 70%. Additionally, it is shown that the improvement in the verification accuracy achieved in this way is higher than that obtainable with the direct use of PMC with GMM-UBM. Moreover, it is found that while the accuracy performance of GMM-SVM can also considerably benefit from the use of these techniques, the extensive computational cost involved in this case severely limits the use of such a combined approach in practice.