Sciweavers

ICASSP
2011
IEEE
13 years 3 months ago
Discriminatively estimated discrete, parametric and smoothed-discrete duration models for speech recognition
Duration of phonemic segments provide important cues for distinguishing words in languages such as Arabic. Recently, we proposed a discriminatively estimated joint acoustic, durat...
Maider Lehr, Izhak Shafran
TASLP
2010
122views more  TASLP 2010»
13 years 6 months ago
Error Approximation and Minimum Phone Error Acoustic Model Estimation
Minimum phone error (MPE) acoustic parameter estimation involves calculation of edit distances (errors) between correct and incorrect hypotheses. In the context of large vocabulary...
Matt Gibson 0002, Thomas Hain
NAACL
1994
14 years 23 days ago
Multilingual Speech Databases at LDC
As multilingual products and technology grow in importance, the Linguistic Data Consortium (LDC) intends to provide the resources needed for research and development activities, e...
John J. Godfrey
FGR
2004
IEEE
87views Biometrics» more  FGR 2004»
14 years 3 months ago
Transition Movement Models for Large Vocabulary Continuous Sign Language Recognition
The major challenges that sign language recognition (SLR) now faces are developing methods that solve large vocabulary continuous sign problems. In this paper, large vocabulary co...
Wen Gao, Gaolin Fang, Debin Zhao, Yiqiang Chen
GW
2005
Springer
119views Biometrics» more  GW 2005»
14 years 5 months ago
A Comparison Between Etymon- and Word-Based Chinese Sign Language Recognition Systems
Hitherto, one major challenge to sign language recognition is how to develop approaches that scale well with increasing vocabulary size. In large vocabulary speech recognition real...
Chunli Wang, Xilin Chen, Wen Gao
PCM
2007
Springer
99views Multimedia» more  PCM 2007»
14 years 5 months ago
Signer Adaptation Based on Etyma for Large Vocabulary Chinese Sign Language Recognition
Sign language recognition (SLR) with large vocabulary and signer independency is valuable and is still a big challenge. Signer adaptation is an important solution to signer indepen...
Yu Zhou, Wen Gao, Xilin Chen, Liang-Guo Zhang, Chu...
ICASSP
2008
IEEE
14 years 5 months ago
Phonetic pronunciations for arabic speech-to-text systems
In this paper two aspects of generating and using phonetic Arabic dictionaries are described. First, the use of single pronunciation acoustic models in the context of Arabic large...
Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Phi...
ICASSP
2009
IEEE
14 years 6 months ago
Discriminative training of hierarchical acoustic models for large vocabulary continuous speech recognition
In this paper we propose discriminative training of hierarchical acoustic models for large vocabulary continuous speech recognition tasks. After presenting our hierarchical modeli...
Hung-An Chang, James R. Glass