Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows
This work addresses robustness in classification for sequential data like speech, but it appears incremental as it builds on existing HMM and normalizing flow methods.
The paper tackled the problem of robust classification for sequential data corrupted by noise by proposing a generative model called NMM-HMM, which combines hidden Markov models with normalizing flow mixtures, and verified improved robustness in speech recognition applications.
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.