Justin Salamon
Justin Salamon
Right now the [scaper tutorial](https://github.com/justinsalamon/scaper/blob/master/docs/tutorial.rst) includes a section about the source separation features, which I think is sufficient for the general tutorial. It would be great to create a separate,...
Currently, if the chosen `event_time` is such that `event_time + event_duration > soundscape_duration`, then `event_time` gets set to `soundscape_duration - event_duration`, since event duration takes priority over the event start...
Right now there aren't any checks related to amplifying events based on their specified SNR values. It would be helpful for Scaper to print out a warning when an event...
Currently when using sox for time stretching, the actual duration of the time stretched event can vary slightly from the estimated duration (estimated = duration * stretch factor). This caused...
`generate_from_jams()` requires updating observations if a new fg/bg path is provided. Currently this is done by updating the value dict directly, which is a hack because in principle the observation...
Right now if a soundscape is "empty" (no background or foreground events) a warning will be issued and no audio will be generated. Ideally we want to synthesize a silent...
We should add guidelines + templates for posting issues and contributing code. There are examples for both in Librosa we could work off of: https://github.com/librosa/librosa/blob/master/CONTRIBUTING.md @jongwook I'm happy to put...
https://coveralls.io/github/marl/crepe
As we update dependencies (e.g. TF), there's a real risk of changed behavior going unnoticed (e.g. performance drop). We should add regression tests to ensure the output remains consistent.
On [core.py#L149](https://github.com/marl/crepe/blob/master/crepe/core.py#L149) we're passing the argmax of pitch salience matrix as observations to the decoder, but shouldn't we be passing the salience matrix directly?