1 |
Streaming cascade-based speech translation leveraged by a direct segmentation model
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Speaker-Adapted Confidence Measures for ASR using Deep Bidirectional Recurrent Neural Networks
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Interactive handwriting recognition with limited user effort
|
|
|
|
BASE
|
|
Show details
|
|
|
|