Masked Proxy Loss For Text-independent Speaker Verification

Abstract

Open-set speaker recognition can be regarded as a metric learning problem, which is to maximize inter-class variance and minimize intra-class variance. Supervised metric learning can be categorized into entity-based learning and proxy-based learning. Most of the existing metric learning objectives like Contrastive, Triplet, Prototypical, GE2E, etc all belong to the former division, the performance of which is either highly dependent on sample mining strategy or restricted by insufficient label information in the mini-batch. Proxy-based losses mitigate both shortcomings, however, fine-grained connections among entities are either not or indirectly leveraged. This paper proposes a Masked Proxy (MP) loss which directly incorporates both proxy-based relationships and pair-based relationships. We further propose Multinomial Masked Proxy (MMP) loss to leverage the hardness of speaker pairs. These methods have been applied to evaluate on VoxCeleb test set and reach state-of-the-art Equal Erro

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keylian2020masked

Related papers

• A Comparison Of Metric Learning Loss Functions For End-to-end Speaker Verification (2020)6.77
• Multi-task Metric Learning For Text-independent Speaker Verification (2020)0.00
• Large Margin Softmax Loss For Speaker Verification (2019)14.66
• Unified Hypersphere Embedding For Speaker Recognition (2018)0.00
• Experimenting With Additive Margins For Contrastive Self-supervised Speaker Verification (2023)4.52
• Meta-learning Framework For End-to-end Imposter Identification In Unseen Speaker Recognition (2023)2.26
• Meta-learning For Short Utterance Speaker Recognition With Imbalance Length Pairs (2020)15.61
• Margin Matters: Towards More Discriminative Deep Neural Network Embeddings For Speaker Recognition (2019)15.25