Changes between Version 7 and Version 8 of AcousticModels


Ignore:
Timestamp:
07/28/06 11:50:18 (16 years ago)
Author:
kmaclean
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • AcousticModels

    v7 v8  
    1212  * therefore about 6 meg per minute! 
    1313  * if we want 140 hours of speech, we will need 50400 Meg or around 50.4Gig (assumes a 1000k per Meg), for Original data. 
    14   * Will likely need at least double that space with the propagation of audio (downsampling, noise reduction, etc.) through version control to create Acoustic Models - therefore need at least '''101Gig''' of storage to meet our stated objective. 
    15   * !VoxForge server currently holds 200 Gig, and, if needed, can easily add additional storage . 
     14  * Will likely need at least double that space with the propagation of audio (downsampling, noise reduction, etc.) through version control to create Acoustic Models - therefore need at least '''100Gig''' of storage to meet our stated objective. 
     15  * !VoxForge server currently holds 200 Gig, and, if needed, can easily add additional storage. 
    1616  * Bandwidth is a greater issue, therefore we will require Peer-to-Peer sharing of audio files (i.e. Bittorrent) - see ticket #11. 
    1717