Sixth European Conference on Speech Communication and Technology
In this paper a fast and effective algorithm named equal feature variance sum (EFVS) frame-synchronous searching is presented for state decoding. EFVS controls the state transition by using only the feature variance of the speech, instead of by using the state dwell distribution. The basic hypothesis of this new algorithm is the equality of feature variance sum in each state of the speech. Given the boundaries of the speech recognition unit (SRU), EFVS can generate the state sequence without dynamic searching. In a continuous speech word recognition system, this novel algorithm reduces the error rate by 36.8% and speed up the system by 65.6% compared with the traditional state decoding methods.
Full Paper (PDF) Gnu-Zipped Postscript
Bibliographic reference. Xu, Mingxing / Zheng, Fang / Wu, Wenhu (1999): "A fast and effective state decoding algorithm", In EUROSPEECH'99, 1255-1258.