| Application:
Speech Recognition |
|
|
|
|
|
|
|
| Speech-to-text
translation of spoken utterances. |
||||||
| Two
dimensions of fidelity: |
||||||
| • | Full or
reduced speech model. |
|||||
| • | Local,
remote, or hybrid recognition. |
|||||
| client |
|
|
|
|
| Remote |
|||
| Janus |
|||
| Server |
|||
| Viceroy |
|
|
|
| Speech |
||
| Front-End |
||
|
|
| Speech |
|
| Warden |
|
|
|
|
|
| Local |
|||
| Janus |
|||
| Server |
|||
