Main Content

Compute delta features

specifies the delta window length.`delta`

= audioDelta(`x`

,`deltaWindowLength`

)

specifies the initial condition of the filter.`delta`

= audioDelta(`x`

,`deltaWindowLength`

,`initialCondition`

)

`[`

also returns the final condition of the filter.`delta`

,`finalCondition`

] = audioDelta(`x`

,___)

The audioDelta function uses a least-squares approximation of the local slope over a
region centered on sample *x*(*k*), which includes
*M* samples before the current sample and *M* samples
after the current sample.

$$delta=\frac{{\displaystyle \sum _{k=-M}^{M}k\text{\hspace{0.17em}}x(k)}}{{\displaystyle \sum _{k=-M}^{M}{k}^{2}}}$$

*M* is equal to
`floor(`

. For details, see [1].`deltaWindowLength`

/2)

[1] Rabiner, Lawrence R., and Ronald
W. Schafer. *Theory and Applications of Digital Speech
Processing*. Upper Saddle River, NJ: Pearson, 2010.

`mfcc`

| `gtcc`

| Extract Audio
Features | `designAuditoryFilterBank`

| `stft`

| `cepstralCoefficients`