paper-with-me

홈 › Papers

Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows

2021-02-15 · Anubhab Ghosh, Antoine Honoré, Dong Liu, Gustav Eje Henter, Saikat Chatterjee

We test the robustness of a maximum-likelihood (ML) based classifier where sequential data as observation is corrupted by noise. The hypothesis is that a generative model, that combines the state transitions of a hidden Markov model (HMM) and the neural network based probability distributions for the hidden states of the HMM, can provide a robust classification performance. The combined model is called normalizing-flow mixture model based HMM (NMM-HMM). It can be trained using a combination of expectation-maximization (EM) and backpropagation. We verify the improved robustness of NMM-HMM classifiers in an application to speech recognition.

📄 PDF Abstract BibTeX arXiv:2102.07284

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationRobust classificationspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability

2021-07-01 · Anubhab Ghosh, Antoine Honoré, Dong Liu, Gustav Eje Henter 외

In pursuit of explainability, we develop generative models for sequential data. The proposed models provide state-of-the-art classification results and robust performance for speech phone classification. We combine moder…

ClassificationDiversity

Generalized Normalizing Flows via Markov Chains

2021-11-24 · Paul Hagemann, Johannes Hertrich, Gabriele Steidl

Normalizing flows, diffusion normalizing flows and variational autoencoders are powerful generative models. This chapter provides a unified framework to handle these approaches via Markov chains. We consider stochastic n…

Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows

2020-07-13 · ICLR 2021 1 · Chris Cannella, Mohammadreza Soltani, Vahid Tarokh

We introduce Projected Latent Markov Chain Monte Carlo (PL-MCMC), a technique for sampling from the high-dimensional conditional distributions learned by a normalizing flow. We prove that a Metropolis-Hastings implementa…

Stochastic Normalizing Flows for Inverse Problems: a Markov Chains Viewpoint

2021-09-23 · Paul Hagemann, Johannes Hertrich, Gabriele Steidl

To overcome topological constraints and improve the expressiveness of normalizing flow architectures, Wu, K\"ohler and No\'e introduced stochastic normalizing flows which combine deterministic, learnable flow transformat…

Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction

2021-06-06 · Janis Postels, Mengya Liu, Riccardo Spezialetti, Luc van Gool 외

Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. However, these flow-based models still requ…

Data AugmentationPoint Cloud Generation