Abstract for valtchev_icslp94

Proc. ICSLP'94

A DYNAMIC NETWORK DECODER DESIGN FOR LARGE VOCABULARY SPEECH RECOGNITION

V. Valtchev, J.J. Odell, P.C. Woodland, and S.J. Young

1994

Accuracy and speed are the main issues to consider when designing a large vocabulary speech recogniser. Recent experience with the Wall Street Journal (WSJ) corpus has shown that high recognition accuracy requires the use of detailed acoustic models in conjunction with well-trained long span language models. In this paper we present a two-pass decoder architecture which extends an original one-pass design. The initial pass consists of a time synchronous backward search in a pre-compiled network using simplified acoustic models and a null grammar. The forward pass can function as a stand-alone one-pass decoder capable of using cross-word context-dependent models and long span language models. The capabilities of this framework are empirically examined in terms of recognition accuracy vs speed on the Wall Street Journal database.


(ftp:) valtchev_icslp94.ps.Z (http:) valtchev_icslp94.ps.Z
PDF (automatically generated from original PostScript document - may be badly aliased on screen):
  (ftp:) valtchev_icslp94.pdf | (http:) valtchev_icslp94.pdf

If you have difficulty viewing files that end '.gz', which are gzip compressed, then you may be able to find tools to uncompress them at the gzip web site.

If you have difficulty viewing files that are in PostScript, (ending '.ps' or '.ps.gz'), then you may be able to find tools to view them at the gsview web site.

We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.