Reducing time-synchronous beam search effort using stage based look-ahead and language model rank based pruning

In this paper, we present an efficient look-ahead technique based on both the Language Model (LM) Look-Ahead and the Acoustic Model (AM) Look-Ahead, for the time-synchronous beam search in the large vocabulary speech recognition. In this so-call stage based look-ahead (SLA) technique, two predicting processes with different hypothesis evaluating criteria are organized by stages according to the different requirements for pruning the unlikely surviving hypotheses. Furthermore, in order to reduce the efforts for distributing the LM over the lexical tree more effectively, the LM Rank based Pruning (LMRP) is integrated with the extension of each new phoneme node. The recognition experiments performed on the 50k-word Mandarin Dictation task (Easytalk2000) show that a reduction by 10 percents in the search effort in comparison with the standard word-conditioned search using LM look-ahead only, and a reduction of 25 percents in the word error rates in comparison with the search algorithm without any look-ahead can be achieved.