Siamese Neural Network with Joint Bayesian Model Structure for Speaker Verification

• URL: http://arxiv.org/abs/2104.03004v1
• Date: Wed, 7 Apr 2021 09:17:29 GMT
• Title: Siamese Neural Network with Joint Bayesian Model Structure for Speaker Verification
• Authors: Xugang Lu, Peng Shen, Yu Tsao, Hisashi Kawai
• Abstract summary: We propose a novel Siamese neural network (SiamNN) for speaker verification. Joint distribution of samples is first formulated based on a joint Bayesian (JB) based generative model. We further train the model parameters with the pair-wised samples as a binary discrimination task for speaker verification.
• Score: 54.96267179988487
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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-wised samples as a binary discrimination task for SV. We carried out SV experiments on data corpus of speakers in the wild (SITW) and VoxCeleb. Experimental results showed that our proposed model improved the performance with a large margin compared with state of the art models for SV.

Related papers

• Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback [97.0874638345205]
  generative models can be great test-time adapters for discriminative models. Our method, Diffusion-TTA, adapts pre-trained discriminative models to each unlabelled example in the test set. We show Diffusion-TTA significantly enhances the accuracy of various large-scale pre-trained discriminative models.
  arXiv  Detail & Related papers  (2023-11-27T18:59:53Z)
• Optimal Transport Model Distributional Robustness [33.24747882707421]
  Previous works have mainly focused on exploiting distributional robustness in the data space. We develop theories that enable us to learn the optimal robust center model distribution. Our framework can be seen as a probabilistic extension of Sharpness-Aware Minimization.
  arXiv  Detail & Related papers  (2023-06-07T06:15:12Z)
• A Hybrid of Generative and Discriminative Models Based on the Gaussian-coupled Softmax Layer [5.33024001730262]
  We propose a method to train a hybrid of discriminative and generative models in a single neural network. We demonstrate that the proposed hybrid model can be applied to semi-supervised learning and confidence calibration.
  arXiv  Detail & Related papers  (2023-05-10T05:48:22Z)
• Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models [56.88106830869487]
  We introduce equi-tuning, a novel fine-tuning method that transforms (potentially non-equivariant) pretrained models into group equivariant models. We provide applications of equi-tuning on three different tasks: image classification, compositional generalization in language, and fairness in natural language generation.
  arXiv  Detail & Related papers  (2022-10-13T08:45:23Z)
• A Statistical-Modelling Approach to Feedforward Neural Network Model Selection [0.8287206589886881]
  Feedforward neural networks (FNNs) can be viewed as non-linear regression models. A novel model selection method is proposed using the Bayesian information criterion (BIC) for FNNs. The choice of BIC over out-of-sample performance leads to an increased probability of recovering the true model.
  arXiv  Detail & Related papers  (2022-07-09T11:07:04Z)
• Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Bounds [20.393359858407162]
  We introduce a framework for Bayesian experimental design (BED) with implicit models, where the data-generating distribution is intractable but sampling from it is still possible. In order to find optimal experimental designs for such models, our approach maximises mutual information lower bounds that are parametrised by neural networks. By training a neural network on sampled data, we simultaneously update network parameters and designs using gradient-ascent.
  arXiv  Detail & Related papers  (2021-05-10T13:59:25Z)
• Statistical inference of the inter-sample Dice distribution for discriminative CNN brain lesion segmentation models [0.0]
  Discriminative convolutional neural networks (CNNs) have performed well in many brain lesion segmentation tasks. segmentation sampling on discriminative CNNs is used to assess a trained model's robustness. A rigorous confidence based decision rule is proposed to decide whether to reject or accept a CNN model for a particular patient.
  arXiv  Detail & Related papers  (2020-12-04T18:18:24Z)
• Statistical model-based evaluation of neural networks [74.10854783437351]
  We develop an experimental setup for the evaluation of neural networks (NNs) The setup helps to benchmark a set of NNs vis-a-vis minimum-mean-square-error (MMSE) performance bounds. This allows us to test the effects of training data size, data dimension, data geometry, noise, and mismatch between training and testing conditions.
  arXiv  Detail & Related papers  (2020-11-18T00:33:24Z)
• Robust Finite Mixture Regression for Heterogeneous Targets [70.19798470463378]
  We propose an FMR model that finds sample clusters and jointly models multiple incomplete mixed-type targets simultaneously. We provide non-asymptotic oracle performance bounds for our model under a high-dimensional learning framework. The results show that our model can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-10-12T03:27:07Z)
• Decision-Making with Auto-Encoding Variational Bayes [71.44735417472043]
  We show that a posterior approximation distinct from the variational distribution should be used for making decisions. Motivated by these theoretical results, we propose learning several approximate proposals for the best model. In addition to toy examples, we present a full-fledged case study of single-cell RNA sequencing.
  arXiv  Detail & Related papers  (2020-02-17T19:23:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.