A Viterbi algorithm for a trajectory model derived from HMM with explicit relationship between static and dynamic features

Citations Over TimeTop 10% of 2004 papers

Abstract

This paper introduces a Viterbi algorithm to obtain a sub-optimal state sequence for trajectory-HMM, which is derived from HMM with explicit relationship between static and dynamic features. The trajectory-HMM can alleviate some limitations of HMM, which are (i) constant statistics within HMM state and (ii) conditional independence of observations given the state sequence, without increasing the number of model parameters. The proposed algorithm was applied to state-boundary optimization for Viterbi training and N-best rescoring. In a speaker-dependent continuous speech recognition experiment, trajectory-HMM with the proposed algorithm achieved about 14% error reduction over the standard HMM with the conventional Viterbi algorithm.

Related Papers

• → Marginalized Viterbi algorithm for hierarchical hidden Markov models(2013)8 cited
• → A Viterbi algorithm for a trajectory model derived from HMM with explicit relationship between static and dynamic features(2004)27 cited
• → A reduced-state Viterbi algorithm for blind sequence estimation of DPSK sources(1999)2 cited
• → Variant of Viterbi algorithm based on p-Norm(2017)1 cited
• Development and Implementation of Soft Output Viterbi Algorithm (SOVA)(2010)