DP-based wordgraph pruning

Author

Kuhn, Thomas ; Fetter, Pablo ; Kaltenmeier, Alfred ; Regel-Brietzmann, Peter

Author_Institution

Dept. of Res. & Technol., Daimler-Benz AG, Ulm, Germany

Volume

2

fYear

1996

fDate

7-10 May 1996

Firstpage

861

Abstract

We present an efficient technique of generating word graphs in a continuous speech recognition system. The word graph is constructed in two stages. In the first stage, a huge word graph is generated as a by-product of a beam-driven forward search. Based on a dynamic-programming (DP) method, this huge word graph will be pruned in the second stage using higher level knowledge, such as n-gram language models. In this pruning stage an edge is removed if there is no path going through this edge which is better scored as the best-scored path in the word graph. The proposed technique is evaluated in the German VERBMOBIL task

Keywords

acoustic signal processing; dynamic programming; grammars; graph theory; natural languages; search problems; speech processing; speech recognition; DP-based wordgraph pruning; German VERBMOBIL task; acoustic-phonetic modelling; beam-driven forward search; best-scored path; continuous speech recognition system; dynamic programming; higher level knowledge; n-gram language models; word graphs generation; Educational technology; Hidden Markov models; Natural languages; Speech analysis; Speech recognition; Tree graphs;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on

Conference_Location

Atlanta, GA

ISSN

1520-6149

Print_ISBN

0-7803-3192-3

Type

conf

DOI

10.1109/ICASSP.1996.543257

Filename

543257