1![Discriminative Training of WFST Factors with Application to Pronunciation Modeling Preethi Jyothi1 , Eric Fosler-Lussier1 , Karen Livescu2 1 Department of Computer Science and Engineering, The Ohio State University, USA Discriminative Training of WFST Factors with Application to Pronunciation Modeling Preethi Jyothi1 , Eric Fosler-Lussier1 , Karen Livescu2 1 Department of Computer Science and Engineering, The Ohio State University, USA](https://www.pdfsearch.io/img/0944de4b22e98bb29a9b5699b229b2c8.jpg) | Add to Reading ListSource URL: ttic.uchicago.eduLanguage: English - Date: 2013-06-03 18:26:59
|
---|
2![A WFST-based Log-linear Framework for Speaking-style Transformation Graham Neubig, Shinsuke Mori, Tatsuya Kawahara Graduate School of Informatics, Kyoto University Sakyo-ku, Kyoto, Japan Abstract A WFST-based Log-linear Framework for Speaking-style Transformation Graham Neubig, Shinsuke Mori, Tatsuya Kawahara Graduate School of Informatics, Kyoto University Sakyo-ku, Kyoto, Japan Abstract](https://www.pdfsearch.io/img/8f8934f2e079988c41f3d5e91b40270d.jpg) | Add to Reading ListSource URL: www.ar.media.kyoto-u.ac.jpLanguage: English - Date: 2009-08-16 12:37:05
|
---|
3![A COMPARATIVE ANALYSIS OF DYNAMIC NETWORK DECODING David Rybach, Ralf Schl¨uter, Hermann Ney Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52056 Aachen, Germany A COMPARATIVE ANALYSIS OF DYNAMIC NETWORK DECODING David Rybach, Ralf Schl¨uter, Hermann Ney Human Language Technology and Pattern Recognition, Computer Science Department, RWTH Aachen University, 52056 Aachen, Germany](https://www.pdfsearch.io/img/623b2ecc202203649a2ea539a7422e61.jpg) | Add to Reading ListSource URL: www-i6.informatik.rwth-aachen.deLanguage: English |
---|
4![3-2 Development of the SprinTra WFST Speech Decoder DIXON Paul Richard, HORI Chiori, and KASHIOKA Hideki In this paper we describe the NICT Weighted Finite State Transducer (WFST) based speech decoder named SprinTra. The 3-2 Development of the SprinTra WFST Speech Decoder DIXON Paul Richard, HORI Chiori, and KASHIOKA Hideki In this paper we describe the NICT Weighted Finite State Transducer (WFST) based speech decoder named SprinTra. The](https://www.pdfsearch.io/img/467cc8fa3c1958e771d749539d6bdb91.jpg) | Add to Reading ListSource URL: www.nict.go.jpLanguage: English - Date: 2013-11-21 21:19:13
|
---|
5![GENERATING EXACT LATTICES IN THE WFST FRAMEWORK Daniel Povey1 , Mirko Hannemann1,2, Gilles Boulianne , Luk´as Burget , Arnab Ghoshal5, Milos Janda2 , Martin Kara´at2, Stefan Kombrink2 , Petr Motl´c ek6 GENERATING EXACT LATTICES IN THE WFST FRAMEWORK Daniel Povey1 , Mirko Hannemann1,2, Gilles Boulianne , Luk´as Burget , Arnab Ghoshal5, Milos Janda2 , Martin Kara´at2, Stefan Kombrink2 , Petr Motl´c ek6](https://www.pdfsearch.io/img/a65a021c6e27af34a811046afb208345.jpg) | Add to Reading ListSource URL: homepages.inf.ed.ac.ukLanguage: English - Date: 2012-06-12 09:45:08
|
---|
6![Harbor Community Monitoring Study Saturation Monitoring of Air Toxics Eric Fujita, David Campbell, Brooks Mason and Barbara Zielinska Division of Atmospheric Sciences Harbor Community Monitoring Study Saturation Monitoring of Air Toxics Eric Fujita, David Campbell, Brooks Mason and Barbara Zielinska Division of Atmospheric Sciences](https://www.pdfsearch.io/img/b048dc1412dcefd07f1623445e3d8d99.jpg) | Add to Reading ListSource URL: www.arb.ca.govLanguage: English - Date: 2008-04-25 17:22:46
|
---|
7![A Fully Data Parallel WFST-based Large Vocabulary Continuous Speech Recognition on a Graphics Processing Unit Jike Chong, Ekaterina Gonina, Youngmin Yi, Kurt Keutzer Department of Electrical Engineering and Computer Scie A Fully Data Parallel WFST-based Large Vocabulary Continuous Speech Recognition on a Graphics Processing Unit Jike Chong, Ekaterina Gonina, Youngmin Yi, Kurt Keutzer Department of Electrical Engineering and Computer Scie](https://www.pdfsearch.io/img/caf9dd819a235713dac0607465e5d6bc.jpg) | Add to Reading ListSource URL: www.eecs.berkeley.eduLanguage: English - Date: 2010-09-14 19:43:54
|
---|