Paper Info
Title
Recent advances in efficient decoding combining on-line transducer composition and smoothed language model incorporation.
Abstract
This paper presents and evaluates our recent efforts on efficient decoding for Large Vocabulary Continuous Speech Recognition in the framework of Weighted Finite State Transducers. We evaluate on-the-fly transducer composition for reduced memory consumption combined with weight smearing for a more time-synchronous language model incorporation. It turns out that in the on-line composition mode weight smoothing within the static part of the network is even more beneficial on run-time to accuracy ratio than in the fully precompiled case. Evaluations are carried out on a state-of-the-art recognition system of 10k words, cross-word triphone acoustic models and trigram language model. In this scenario, the Viterbi-search is carried out fully time-synchronously in only a single pass. The combination of on-the-fly network composition with only the unigram part of the language model smoothly compiled into the network achieves a remarkably good run-time to accuracy ratio with only moderate memory requirements.
Year
DOI
Venue
2002
10.1109/ICASSP.2002.5743817
ICASSP
Keywords
Field
DocType
artificial neural networks,argon,hidden markov models,minimization
Triphone,Computer science,Speech recognition,Smoothing,Minification,Decoding methods,Artificial neural network,Hidden Markov model,Vocabulary,Language model
Conference
Volume
ISSN
ISBN
1
1520-6149
0-7803-7402-9
Citations 
PageRank 
References 
14
1.65
6
Authors
2
Name
Order
Citations
PageRank
Daniel Willett1141.65
Shigeru Katagiri2850114.01