2007 IEEE Workshop on Automatic Speech Recognition &Amp; Understanding (ASRU) 2007
DOI: 10.1109/asru.2007.4430156
|View full text |Cite
|
Sign up to set email alerts
|

An algorithm for fast composition of weighted finite-state transducers

Abstract: In automatic speech recognition based on weighted-finite transducers, a static decoding graph HC • L • G is typically constructed. In this work, we first show how the size of the decoding graph can be reduced and the necessity of determinizing it can be eliminated by removing the ambiguity associated with transitions to the backoff state or states in G. We then show how the static construction can be avoided entirely by performing fast on-the-fly composition of HC and L • G. We demonstrate that speech recognit… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
12
0

Year Published

2009
2009
2014
2014

Publication Types

Select...
3
3
2

Relationship

2
6

Authors

Journals

citations
Cited by 12 publications
(12 citation statements)
references
References 20 publications
0
12
0
Order By: Relevance
“…Component n-gram probabilities and interpolation weights will be applied for each context on request during decoding. Similar approaches have been previously shown to be effective for the composition between one single back-off n-gram LM and a lexicon transducer (Caseiro and Trancoso, 2006;Cheng et al, 2007;McDonough et al, 2007;Oonishi et al, 2009).…”
Section: Decoding With Context Dependent Lm Interpolationmentioning
confidence: 79%
“…Component n-gram probabilities and interpolation weights will be applied for each context on request during decoding. Similar approaches have been previously shown to be effective for the composition between one single back-off n-gram LM and a lexicon transducer (Caseiro and Trancoso, 2006;Cheng et al, 2007;McDonough et al, 2007;Oonishi et al, 2009).…”
Section: Decoding With Context Dependent Lm Interpolationmentioning
confidence: 79%
“…Finally, M 1 is composed on-the-fly with a hidden Markov model H along with the cross-word computation. This was initially described by Hori et al [22], [23] and further improved by McDonough et al [24] and Allaucen et al [25], [26]. The probability for a phoneme sequence given a sequence of speech features can be computed [27] using a token passing time synchronous Viterbi beam search [28].…”
Section: Recognition On the Servermentioning
confidence: 99%
“…If the new filter state is not the blocking state ⊥ and a new transition is created from the filter-rewritten transitions (e ′ 1 , e ′ 2 ) (line 14). If the destination state (n[e ′ 1 ], n[e ′ 2 ], q ′ 3 ) has not been found previously, it is added to Q and inserted in S (lines [11][12][13]. The composition algorithm presented here is available in the OpenFst library [3].…”
Section: Compositionmentioning
confidence: 99%
“…For some problems, it is possible to find equivalent inputs that will compose more efficiently, but it is not always possible or desirable to do so. This has been especially an issue in natural language processing applications and led to special-purpose composition algorithms for use in speech recognition [6,7,11,15] and speech synthesis [2].…”
Section: Introductionmentioning
confidence: 99%