An efficient algorithm for sequentially finding the N-best list

We propose a novel method to obtain the N-best list of hypotheses produced by a speech recognizer. The proposed procedure is based on eeciently computation of the N most likely state sequences of a hidden Markov model. We show that the entire information needed to compute the N-best list from the HMM trellis graph is encapsulated in entities that can be computed in a single forward-backward iteration that usually yields the most likely state sequence. The hypotheses list can then be extracted in a sequential manner from these entities without the need to refer back to the original data of the HMM.