Sciweavers

127 search results - page 10 / 26
» Advances in Large Vocabulary Continuous Speech Recognition
Sort
View
ICASSP
2011
IEEE
12 years 11 months ago
Machine and acoustical condition dependency analyses for fast acoustic likelihood calculation techniques
The acceleration of acoustic likelihood calculation has been an important research issue for developing practical speech recognition systems. And there are various specification ...
Atsunori Ogawa, Satoshi Takahashi, Atsushi Nakamur...
NAACL
2010
13 years 5 months ago
Contextual Information Improves OOV Detection in Speech
Out-of-vocabulary (OOV) words represent an important source of error in large vocabulary continuous speech recognition (LVCSR) systems. These words cause recognition failures, whi...
Carolina Parada, Mark Dredze, Denis Filimonov, Fre...
ICASSP
2010
IEEE
13 years 7 months ago
Speech modeling based on committee-based active learning
We propose a committee-based active learning method for large vocabulary continuous speech recognition. In this approach, multiple recognizers are prepared beforehand, and the rec...
Yuzu Hamanaka, Koichi Shinoda, Sadaoki Furui, Tada...
ICASSP
2011
IEEE
12 years 11 months ago
Using morpheme and syllable based sub-words for polish LVCSR
Polish is a synthetic language with a high morpheme-perword ratio. It makes use of a high degree of inflection leading to high out-of-vocabulary (OOV) rates, and high Language Mo...
M. Ali Basha Shaik, Amr El-Desoky Mousa, Ralf Schl...
NAACL
1994
13 years 8 months ago
Session 13: CSR Search
This session had five papers related to different topics in CSR Search. The topics ranged from integration of many knowledge sources within a practical system, to different search...
Richard M. Schwartz