Fast look-ahead pruning strategies in continuous speech recognition

The author presents two fast anticipatory pruning schemes that have been investigated within the frame of a continuous speech recognition system based on HMM (hidden Markov modeling) and Viterbi decoding. Both algorithms rest on a coarse acoustic analysis in five broad phonetic categories. The first strategy interacts with the phoneme transitions during the search process, while the second takes account of lexical constraints by operating at the word level. Experiments have been performed on a thousand-word continuous speech task with no language model. Results show that a significant computational reduction is feasible without impairing the overall accuracy