Coupling A Generative Model With A Discriminative Learning Framework For Speaker Verification

Abstract

The speaker verification (SV) task is to decide whether an utterance is spoken by a target or an imposter speaker. For most studies, a log-likelihood ratio (LLR) score is estimated based on a generative probability model on speaker features and compared with a threshold for making a decision. However, the generative model usually focuses on individual feature distributions, does not have the discriminative feature selection ability, and is easy to be distracted by nuisance features. The SV could be formulated as a binary discrimination task where neural network-based discriminative learning could be applied. In discriminative learning, the nuisance features could be removed with the help of label supervision. However, discriminative learning pays more attention to classification boundaries and is prone to overfitting to a training set which may result in bad generalization on a test set. Thus, we propose a hybrid learning framework, i.e., coupling a joint Bayesian (JB) generative model

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keylu2021coupling

Related papers

• Siamese Neural Network With Joint Bayesian Model Structure For Speaker Verification (2021)0.00
• Gmm-resnext: Combining Generative And Discriminative Models For Speaker Verification (2024)4.52
• Cross-lingual Speaker Verification With Deep Feature Learning (2017)8.35
• Speaker Verification In Multi-speaker Environments Using Temporal Feature Fusion (2022)0.00
• Generative Adversarial Speaker Embedding Networks For Domain Robust End-to-end Speaker Verification (2018)0.00
• Joint Bayesian Gaussian Discriminant Analysis For Speaker Verification (2016)3.58
• Speaker Verification Using Convolutional Neural Networks (2018)0.00
• Generative X-vectors For Text-independent Speaker Verification (2018)7.16