Siamese Neural Network With Joint Bayesian Model Structure For Speaker Verification
2021 · Xugang Lu, Peng Shen, Yu Tsao, et al.
Abstract
Generative probability models are widely used for speaker verification (SV). However, the generative models are lack of discriminative feature selection ability. As a hypothesis test, the SV can be regarded as a binary classification task which can be designed as a Siamese neural network (SiamNN) with discriminative training. However, in most of the discriminative training for SiamNN, only the distribution of pair-wised sample distances is considered, and the additional discriminative information in joint distribution of samples is ignored. In this paper, we propose a novel SiamNN with consideration of the joint distribution of samples. The joint distribution of samples is first formulated based on a joint Bayesian (JB) based generative model, then a SiamNN is designed with dense layers to approximate the factorized affine transforms as used in the JB model. By initializing the SiamNN with the learned model parameters of the JB model, we further train the model parameters with the pair
Authors
(none)
Tags
Stats
Related papers
- Coupling A Generative Model With A Discriminative Learning Framework For Speaker Verification (2021)5.24
- Speaker Verification Using Convolutional Neural Networks (2018)0.00
- Joint Bayesian Gaussian Discriminant Analysis For Speaker Verification (2016)3.58
- Gmm-resnext: Combining Generative And Discriminative Models For Speaker Verification (2024)4.52
- Prosodic-enhanced Siamese Convolutional Neural Networks For Cross-device Text-independent Speaker Verification (2018)8.35
- Self-supervised Speaker Verification With Simple Siamese Network And Self-supervised Regularization (2021)10.85
- Joint Speaker Encoder And Neural Back-end Model For Fully End-to-end Automatic Speaker Verification With Multiple Enrollment Utterances (2022)0.00
- Bayesian X-vector: Bayesian Neural Network Based X-vector System For Speaker Verification (2020)6.77