Effect of multicondition training on i-vector PLDA configurations for speaker recognition

摘要

The i-vector representation and PLDA classifier have shown state-of-the-art performance for speaker recognition systems. The availability of more than one enrollment utterance for a speaker allows a variety of configurations which can be used to enhance robustness to noise. The well-known technique of multicondition training can be utilized at different stages of the system, including enrollment and classifier training. We also study the effect of mismatched training, averaging and length normalization. Our study indicates that multicondition training of the PLDA model, and if possible the enrollment i-vectors are the most important to achieve good performance in noisy evaluation data.