Powering Hidden Markov Model by Neural Network based Generative Models
This work addresses the need for more powerful sequential data modeling in domains like speech or bioinformatics, but it appears incremental as it combines existing HMM and neural network techniques.
The authors tackled the problem of enhancing Hidden Markov Models (HMMs) for sequential data modeling by integrating neural network-based generative models, resulting in a new model called GenHMM that demonstrated efficiency in classification tasks on practical sequential data.
Hidden Markov model (HMM) has been successfully used for sequential data modeling problems. In this work, we propose to power the modeling capacity of HMM by bringing in neural network based generative models. The proposed model is termed as GenHMM. In the proposed GenHMM, each HMM hidden state is associated with a neural network based generative model that has tractability of exact likelihood and provides efficient likelihood computation. A generative model in GenHMM consists of mixture of generators that are realized by flow models. A learning algorithm for GenHMM is proposed in expectation-maximization framework. The convergence of the learning GenHMM is analyzed. We demonstrate the efficiency of GenHMM by classification tasks on practical sequential data. Code available at https://github.com/FirstHandScientist/genhmm.