mlsanityData to 7 Oct 2026

Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows

arXiv 2102.07284 ↗First posted 15 Feb 2021cs.LG eess.SPcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 11 of its 18 references that are in the map. First posted on arXiv 15 Feb 2021.

Builds on

11 of 18 references.

References · 11

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Density estimation using Real NVPcited by 2,029
  3. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  4. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  5. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  6. 2015Attention-Based Models for Speech Recognitioncited by 400
  7. 2018Light Gated Recurrent Units for Speech Recognitioncited by 48
  8. 2018The PyTorch-Kaldi Speech Recognition Toolkitcited by 38
  9. 2019Normalizing Flows: An Introduction and Review of Current Methodscited by 16
  10. 2019Powering Hidden Markov Model by Neural Network based Generative Modelscited by 7
  11. 2019Neural Network based Explicit Mixture Models and Expectation-maximization based Learningcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2.

4 papers.

  1. 2022Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Modelscited by 188
  2. 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 29
  3. 2022OverFlow: Putting flows on top of neural transducers for better TTScited by 8
  4. 2021Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainabilitycited by 4