Multi-session PLDA Scoring of I-vector for Partially Open-Set Speaker Detection

Kong Aik Lee (1) , Anthony Larcher (1) , Chang Huai You (1) , Bin Ma (1) , Haizhou Li (1)

1 Institute for Infocomm Research - I²R [Singapore]

This paper advocates the use of probabilistic linear discriminant analysis (PLDA) for partially open-set detection task with multiple i-vectors enrollment condition. Also referred to as speaker verification, the speaker detection task has always been considered under an open-set scenario. In this paper, a more general partially open-set speaker detection problem in considered, where the imposters might be one of the known speakers previously enrolled to the system. We show how this could be coped with by modifying the definition of the alternative hypothesis in the PLDA scoring function. We also look into the impact of the conditional-independent assumption as it was used to derive the PLDA scoring function with multiple training i-vectors. Experiments were conducted using the NIST 2012 Speaker Recognition Evaluation (SRE'12) datasets to validate various points discussed in the paper.

Domaines: Informatique [cs]; Intelligence artificielle [cs.AI]

Kong Aik Lee, Anthony Larcher, Chang Huai You, Bin Ma, Haizhou Li. Multi-session PLDA Scoring of I-vector for Partially Open-Set Speaker Detection. Annual Conference of the International Speech Communication Association (Interspeech), Aug 2013, Lyon, France. ⟨hal-01927584⟩