Changes between Version 6 and Version 7 of AcousticModels


Ignore:
Timestamp:
07/28/06 11:14:20 (15 years ago)
Author:
kmaclean
Comment:

--

Legend:

Unmodified
Added
Removed
Modified

  • AcousticModels

    v6 v7  
    1010 
    1111  * for 48kHz:16bit audio, 5 seconds of audio takes 500k. 
    12   * therefore about 30 meg per minute! 
    13   * if we want 140 hours of speech, we will need 252000 Meg or around 252Gig (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. 
    15   * !VoxForge server currently holds 200 Gig, but can easily add additional storage. 
    16   * Bandwidth is a greater issue, therefore require Peer-to-Peer sharing of audio files (i.e. Bittorrent) - see ticket #11. 
     12  * therefore about 6 meg per minute! 
     13  * 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 . 
     16  * Bandwidth is a greater issue, therefore we will require Peer-to-Peer sharing of audio files (i.e. Bittorrent) - see ticket #11. 
    1717