Minimum error rate training (MERT) involves choosing parameter values for a machine translation (MT) system that maximize performance on a tuning set as measured by an automatic e...
The number of video clips available online is growing at a tremendous pace. Conventionally, user-supplied metadata text, such as the title of the video and a set of keywords, has ...
Mehmet Emre Sargin, Hrishikesh Aradhye, Pedro J. M...
We present generative models dedicated to face recognition. Our models consider data extracted from color face images and use Bayesian Networks to model relationships between diffe...
After the handwritten segmentation process, it is common to have connected digits. This is due to the great size and shape digit variations. In addition, the acquisition and the b...
Cristiano de Santana Pereira, George D. C. Cavalca...
— Missing feature theory (MFT) has demonstrated great potential for improving the noise robustness in speech recognition. MFT was mostly applied in the log-spectral domain since ...