An efficient A* stack decoder algorithm for continuous speech recognition with a stochastic language model

D.B. Paul
1992 [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing  
The stack decoder is an attractive algorithm for controlling the acoustic and language model matching in a continuous speech recognizer. A previous paper described a near-optimal admissible Viterbi A* search algorithm for use with noncross-word acoustic models and no-grammar language models [16]. This paper extends this algorithm to include unigram language models and describes a modified version of the algorithm which includes the full (forward) decoder, cross-word acoustic models and
more » ... an language models. The resultant algorithm is not admissible, but has been demonstrated to have a low probability of search error and to be very efficient.
doi:10.1109/icassp.1992.225981 dblp:conf/icassp/Paul92 fatcat:kr6pvbo6qvenlhsfiwvd67dmfu