Main Content

Estimate pitch with deep learning neural network

specifies options using one or more `f0`

= pitchnn(`audioIn`

,`fs`

,`Name,Value`

)`Name,Value`

arguments. For
example, `f0 = pitchnn(audioIn,fs,'ConfidenceThreshold',0.5)`

sets the
confidence threshold for each value of `f0`

to
`0.5`

.

`[`

returns the activations of a `f0`

,`loc`

,`activations`

] = pitchnn(___)`crepe`

pretrained network.

`pitchnn(___)`

with no output arguments plots the
estimated fundamental frequency over time.

[1] Kim, Jong Wook, Justin Salamon,
Peter Li, and Juan Pablo Bello. “Crepe: A Convolutional Representation for Pitch Estimation.”
In *2018 IEEE International Conference on Acoustics, Speech and Signal
Processing (ICASSP)*, 161–65. Calgary, AB: IEEE, 2018.
https://doi.org/10.1109/ICASSP.2018.8461329.