63 search results - page 6 / 13 » Large Vocabulary Audio-Visual Speech Recognition Using Activ... |
NAACL
1994
13 years 9 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
2009
IEEE
14 years 2 months ago
2009
IEEE
We introduce a direct model for speech recognition that assumes an unstructured, i.e., flat text output. The flat model allows us to model arbitrary attributes and dependences o...
CIRA
2007
IEEE
13 years 11 months ago
2007
IEEE
This paper proposes a technique for real-time recognition of facial Identity and expression which uses the active appearance model (AAM) with efficient second order minimization al...
ISCAS
2008
IEEE
14 years 2 months ago
2008
IEEE
Abstract— Especially for tasks like automatic meeting transcription, it would be useful to automatically recognize speech also while multiple speakers are talking simultaneously....
INTERSPEECH
2010
13 years 2 months ago
2010
Over the years, the focus in noise robust speech recognition has shifted from noise robust features to model based techniques such as parallel model combination and uncertainty de...