September 22-25, 1997
In this paper, we describe the new BBN BYBLOS ef- ficient 2-Pass N-Best decoder used for the 1996 Hub-4 Benchmark Tests. The decoder uses a quick fastmatch to determine the likely word endings. Then in the second pass, it performs a time-synchronous beam search using a detailed continuous-density HMM and a trigram language model to decide the word starting positions. From these word starts, the decoder, without looking at the input speech, constructs a trigram word lattice, and generates the top N likely hypotheses. This new 2-pass N-Best decoder maintains comparable recognition performance as the old 4-pass N-Best decoder, while its search strategy is simpler and much more efficient.
Bibliographic reference. Nguyen, Long / Schwartz, Richard (1997): "Efficient 2-pass n-best decoder", In EUROSPEECH-1997, 167-170.