Timeline for MFCCs and mean normalization
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 28, 2020 at 10:15 | history | migrated | from stats.stackexchange.com (revisions) | ||
| Jan 28, 2020 at 0:40 | vote | accept | Abdulkader | ||
| Jan 27, 2020 at 21:17 | comment | added | Nikolay Shmyrev | Speed is the same. As for per-file vs per-database it is basic math, there are no references. 1 second is pretty short for per-file normalization, you might not get improvement from it. | |
| Jan 27, 2020 at 19:49 | comment | added | Abdulkader | And does per-file normalization instead of per-dataset normalization affect the training process (i.e. slow down)? | |
| Jan 27, 2020 at 18:10 | comment | added | Abdulkader | Could you give more details and a useful reference for the block: "Per-file normalization ... etc.", please? However, each wave file in my dataset is one-second length speech command (one-word per file). Thank you. | |
| Jan 27, 2020 at 13:20 | history | answered | Nikolay Shmyrev | CC BY-SA 4.0 |