457 search results - page 12 / 92 » Universal background model based speech recognition |
102
click to vote
NAACL
1994
14 years 11 months ago
1994
The key problem to be faced when building a HMM-based continuous speech recogniser is maintaining the balance between model complexity and available training data. For large vocab...
ICASSP
2011
IEEE
14 years 1 months ago
2011
IEEE
Previously we have proposed different models for estimating articulatory gestures and vocal tract variable (TV) trajectories from synthetic speech. We have shown that when deploye...
ICMI
2003
Springer
15 years 3 months ago
2003
Springer
Gesture recognition is becoming a more common interaction tool in the fields of ubiquitous and wearable computing. Designing a system to perform gesture recognition, however, can...
ACL
2008
14 years 11 months ago
2008
Grounded language models represent the relationship between words and the non-linguistic context in which they are said. This paper describes how they are learned from large corpo...
ICASSP
2011
IEEE
2011
IEEE
A wavelet-based data imputation approach to spectrogram reconstruction for robust speech recognition
14 years 1 months ago
Data imputation approaches for robust automatic speech recognition reconstruct noise corrupted spectral information by exploiting prior knowledge of the relationship between targe...