Ticket #4 (closed task: fixed)
Telephony Multi-User Acoustic Models (8kHz:16-bit)
Reported by: | kmaclean | Owned by: | kmaclean |
---|---|---|---|
Priority: | blocker | Milestone: | Unassigned |
Component: | Acoustic Model | Version: | 0.1-alpha |
Keywords: | Cc: |
Description (last modified by kmaclean) (diff)
Need Telephony Multi-user Acoustic Model for users to download (8kHz/16-bit). These can also be used for Desktop Command and Control
Change History
comment:3 Changed 15 years ago by kmaclean
- Priority changed from major to critical
This is an on-going task, but for release 0.1 beta, need cmu an4 and pda spoken audio corpora integrated into the !Voxforge Multi-User Acoustic Model.
Once these are completed for telephony models (8kHz:16bit), create Acoustic Model for Desktop speech recognition (16kHz:16bit)
comment:5 Changed 15 years ago by kmaclean
- Description modified (diff)
- Summary changed from Multi-User Acoustic Models to Telephony Multi-User Acoustic Models (16kHz:16-bit)
comment:6 Changed 15 years ago by kmaclean
- Milestone changed from 0.1-beta to 0.1-gamma
Moving integration of cmu an4 and pda spoken audio corpora into Voxforge Multi-User Acoustic Model to a later Milestone.
Note: See
TracTickets for help on using
tickets.