Conference paper

POVEY Daniel, HANNEMANN Mirko, BOULIANNE Gilles, BURGET Lukáš, GHOSHAL Arnab, JANDA Miloš, KARAFIÁT Martin, KOMBRINK Stefan, MOTLÍČEK Petr, QIAN Yanmin, RIEDHAMMER Korbinian, VESELÝ Karel and VU Ngoc Thang. Generating Exact Lattices in The WFST Framework. In: Proceedings of 2012 IEEE International Conference on Acoustics, Speech and Signal Processing. Kyoto: IEEE Signal Processing Society, 2012, pp. 4213-4216. ISBN 978-1-4673-0044-5.
Publication language:english
Original title:Generating Exact Lattices in The WFST Framework
Title (cs):Generování přesných svazů v rámci WFST
Pages:4213-4216
Proceedings:Proceedings of 2012 IEEE International Conference on Acoustics, Speech and Signal Processing
Conference:The 37th International Conference on Acoustics, Speech, and Signal Processing
Place:Kyoto, JP
Year:2012
ISBN:978-1-4673-0044-5
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2012/povey_icassp2012_0004213.pdf [PDF]
Keywords
Speech Recognition, Lattice Generation
Annotation
This article describes a lattice generation method, which is most directly applicable when using WFST decoders.
Abstract
We describe a lattice generation method that is exact, i.e. it satisfies all the natural properties we would want from a lattice of alternative transcriptions of an utterance. This method does not introduce substantial overhead above one-best decoding. Our method is most directly applicable when using WFST decoders where the WFST is "fully expanded", i.e. where the arcs correspond to HMM transitions. It outputs lattices that include state-level alignments as well as word labels. The general idea is to create a state-level lattice during decoding, and to do a special form of determinization that retains only the best-scoring path for each word sequence. This special determinization algorithm is a solution to the following problem: Given a WFST A, compute a WFST B that, for each input-symbolsequence of A, contains just the lowest-cost path through A. Our solution always works if the projection of A on its input labels is determinizable, e.g. if A is acyclic.
BibTeX:
@INPROCEEDINGS{
   author = {Daniel Povey and Mirko Hannemann and Gilles Boulianne and
	Luk{\'{a}}{\v{s}} Burget and Arnab Ghoshal and Milo{\v{s}}
	Janda and Martin Karafi{\'{a}}t and Stefan Kombrink and Petr
	Motl{\'{i}}{\v{c}}ek and Yanmin Qian and Korbinian
	Riedhammer and Karel Vesel{\'{y}} and Thang Ngoc Vu},
   title = {Generating Exact Lattices in The WFST Framework},
   pages = {4213--4216},
   booktitle = {Proceedings of 2012 IEEE International Conference on
	Acoustics, Speech and Signal Processing},
   year = {2012},
   location = {Kyoto, JP},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4673-0044-5},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=9914}
}

Your IPv4 address: 54.226.172.30
Switch to IPv6 connection

DNSSEC [dnssec]