4th International Conference on Spoken Language Processing
Philadelphia, PA, USA
Pruning is an essential paradigm to build HMM-based large vocabulary speech recognisers that use reasonable computing resources. Unlikely sentence, word or subword hypotheses are removed from the search space when their likelihood falls outside a beam relative to the best scoring hypothesis. A method for automatically steering this beam such that the search space attains a predefined size is presented.
Bibliographic reference. Hamme, Hugo van / Aelten, Filip van (1996): "An adaptive-beam pruning technique for continuous speech recognition", In ICSLP-1996, 2083-2086.