Generating Exact Lattices in the WFST Framework

  • 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 HMM-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-symbol-sequence of A, contains just the lowest-cost path through A.

Export metadata

Additional Services

Search Google Scholar
Author:Daniel Povey, Mirko Hannemann, Gilles Boulianne, Lukáš Burget, Arnab Ghoshal, Miloš Janda, Martin Karafiát, Stefan Kombrink, Petr Motlíček, Yanmin Qian, Korbinian Riedhammer, Karel Veselý, Ngoc Thang Vu
Parent Title (English):2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, May 2012.
Document Type:Conference Proceeding
Publication Year:2012
Tag:Lattice Generation; Speech Recognition
First Page:4213
Last Page:4216
faculties / departments:Fakultät für Informatik
Dewey Decimal Classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 000 Informatik, Informationswissenschaft, allgemeine Werke