8 search results - page 2 / 2 » Compact Representations by Finite-State Transducers |
INTERSPEECH
2010
13 years 11 days ago
2010
The emergence of highly parallel computing platforms is enabling new trade-offs in algorithm design for automatic speech recognition. It naturally motivates the following investig...
EMNLP
2008
13 years 7 months ago
2008
To improve the Mandarin large vocabulary continuous speech recognition (LVCSR), a unified framework based approach is introduced to exploit multi-level linguistic knowledge. In th...
SIGIR
2003
ACM
13 years 10 months ago
2003
ACM
Translation of proper names is generally recognized as a significant problem in many multi-lingual text and speech processing applications. Even when large bilingual lexicons use...