We survey the use of weighted finite-state transducers (WFSTs) in speech recognition. We show that WFSTs provide a common and natural representation for hidden Markov models (HMMs), context-dependency, pronunciation dictionaries, grammars, and alternative recognition outputs. Furthermore, general tr
β¦ LIBER β¦
Flexible and Expandable Speech Recognition Hardware with Weighted Finite State Transducers
β Scribed by Kisun You; Jungwook Choi; Wonyong Sung
- Book ID
- 106559759
- Publisher
- Springer US
- Year
- 2011
- Tongue
- English
- Weight
- 320 KB
- Volume
- 66
- Category
- Article
- ISSN
- 1939-8018
No coin nor oath required. For personal study only.
π SIMILAR VOLUMES
Weighted finite-state transducers in spe
β
Mehryar Mohri; Fernando Pereira; Michael Riley
π
Article
π
2002
π
Elsevier Science
π
English
β 215 KB
Springer Handbook of Speech Processing |
β
Benesty, Jacob; Sondhi, M. Mohan; Huang, Yiteng (Arden)
π
Article
π
2008
π
Springer Berlin Heidelberg
π
German
β 952 KB
From common consumer products such as cell phones and MP3 players to more sophisticated projects such as human-machine interfaces and responsive robots, speech technologies are now everywhere. Many think that it is just a matter of time before more applications of the science of speech become inesca
Learning a Discriminative Weighted Finit
β
Lehr, M.; Shafran, I.
π
Article
π
2011
π
Institute of Electrical and Electronics Engineers
π
English
β 638 KB
Efficient and Robust Music Identificatio
β
Mohri, M.; Moreno, P.J.; Weinstein, E.
π
Article
π
2010
π
Institute of Electrical and Electronics Engineers
π
English
β 750 KB
[Lecture Notes in Computer Science] Patt
β
Sanches, JoΓ£o M.; MicΓ³, Luisa; Cardoso, Jaime S.
π
Article
π
2013
π
Springer Berlin Heidelberg
β 233 KB