CONF Povey_ICASSP_2012/IDIAP Generating Exact Lattices in The WFST Framework Povey, Daniel Hannemann, Mirko Boulianne, Gilles Burget, Lukas Ghoshal, Arnab Janda, Milos Karafiat, Martin Kombrink, Stefan Motlicek, Petr Qian, Yanmin Riedhammer, Korbinian Vesely, Karel Vu, Ngoc Thang EXTERNAL http://publications.idiap.ch/attachments/papers/2022/Povey_ICASSP_2012.pdf PUBLIC The 37th International Conference on Acoustics, Speech, and Signal Processing, Kyoto, JP - Proceedings of 2012 IEEE International Conference on Acoustics, Speech and Signal Processing. Kyoto, Japan 2012 IEEE Signal Processing Societ 4213-4216 978-1-4673-0044-5 10.1109/ICASSP.2012.6288848 doi We describe a lattice generation method that is exact, i.e. it satisfies all the natural properties we would want from a lattice of alterna- tive 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 transi- tions. 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 spe- cial 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.