Audimus.media (seminar): Difference between revisions
From HLT@INESC-ID
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
__NOTOC__ | __NOTOC__ | ||
{{infobox|name=Hugo Meinedo | |||
|username=meinedo | |||
|contact=hugo.meinedo | |||
|phone=+351-213-100-315 | |||
|fax=+351-213-145-843 | |||
}} | |||
== Date == | == Date == | ||
Latest revision as of 12:09, 25 January 2007
 |
|---|
Date
- 14:30, January 26, 2007
- 3rd floor meeting room
Speaker
Abstract
The presentation will review briefly our current Broadcast News automatic speech recognition system, Audimus.media and will focus in recent and future enhancements:
- Unsupervised annotation of training data
- Gender dependent acoustic models
- Speaker dependent acoustic models