A Novel Training Algorithm for HMMs with Partial and Noisy Access to the States

TL;DR

This paper introduces a new training algorithm for Hidden Markov Models that leverages partial and noisy side information about hidden states, significantly improving state recognition accuracy and robustness.

Contribution

It develops a novel EM-based algorithm that incorporates partial and noisy state labels into HMM training, enhancing performance over traditional methods.

Findings

Up to 70% improvement in state recognition accuracy.

Algorithm is robust to various training conditions.

Effective in scenarios with partial and noisy state information.

Abstract

This paper proposes a new estimation algorithm for the parameters of an HMM as to best account for the observed data. In this model, in addition to the observation sequence, we have \emph{partial} and \emph{noisy} access to the hidden state sequence as side information. This access can be seen as "partial labeling" of the hidden states. Furthermore, we model possible mislabeling in the side information in a joint framework and derive the corresponding EM updates accordingly. In our simulations, we observe that using this side information, we considerably improve the state recognition performance, up to 70%, with respect to the "achievable margin" defined by the baseline algorithms. Moreover, our algorithm is shown to be robust to the training conditions.