| Feature
extraction: |
|
|
|
|
|
|
|
|
|
|
|
| ¡ | Derive the
formant parameters from the |
|||||||||
| physical model
of human voice organ |
||||||||||
| with mean value |
||||||||||
| ¡ | Synthesize the
pitch with the above |
|||||||||
| parameters. |
||||||||||
| ¡ | Use
autocorrelation method to track |
|||||||||
| pitches
positions of the synthesized pitch |
||||||||||
| ¡ | Use these pitch
positions to extract the |
|||||||||
| pitch of input
hummed data |
||||||||||