Timeline for How to decide the number of cepstral coefficients?
Current License: CC BY-SA 3.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 3, 2013 at 19:36 | vote | accept | Morten | ||
| Mar 26, 2013 at 15:09 | comment | added | Morten | @Nikolay Yes their is no real argument for using the Mel-scale but i guess Cepstral coefficients still can be used as feature for my classifier. | |
| Mar 26, 2013 at 13:23 | comment | added | Nikolay Shmyrev | Then you probably don't need mel coefficients at all. Mel is specifically targetted to human speech. It all depends on the nature of the signals. | |
| Mar 26, 2013 at 11:22 | comment | added | Morten | I need to binary classify non-human audio signals, with little change over time, does that indicate that I fewer or more coefficients? | |
| Mar 25, 2013 at 3:38 | comment | added | user13107 | It should be noted that this answer is specific to "speech" recognition. For speaker recognition, higher cepstral coefficients are more important. | |
| Mar 21, 2013 at 14:57 | comment | added | Morten | Hi, thank you for the response. I guess we will have to allocate some computing power for select an optimal number of coefficients too along with the frame length:-) | |
| Mar 21, 2013 at 14:56 | vote | accept | Morten | ||
| Apr 3, 2013 at 19:36 | |||||
| Mar 21, 2013 at 14:47 | vote | accept | Morten | ||
| Mar 21, 2013 at 14:56 | |||||
| Mar 18, 2013 at 3:27 | history | edited | datageist♦ | CC BY-SA 3.0 |
Made it obvious that the entire answer is a quote.
|
| Mar 17, 2013 at 13:03 | history | answered | Nikolay Shmyrev | CC BY-SA 3.0 |