Guo Zixun Nicolas

Hi Geraint, Thank you for the amazing work. Let me explain my problem first, I want to use the spectrum match to match one audio to the other. And I...

Hi seokju, I have similar problem like the picture below  Even though I tried SCNN but I believe the postprocessing step is similar. below is my result  the...

Lack of validation set?

3

Hi there, Thanks for the implementation! Appreciate if you could share more insight on why there's no valiadtion/test set involved during training? Best,

Monitoring validation loss

1

Hi there, Thanks for the implementation. It's really well written! May I ask whether there's a need to add a validation function to monitor the validation loss as well? Seems...

Hi there, Thank you for your work! It's lot's of help. But I think this code has some discrepancy with the original paper and original theano implementation and may lead...

May I know what's the loss during your training? My loss converges around 0.5. Is that too big?

the paper mentions 1087 clips but the midi folder contains 1078/1071 files

2

Hi there, Thank you for your effort in putting together this dataset. The paper mentions 1087 clips but the midi folder contains only 1078/1071 files (in v2.2). Could you please...

Mismatch between pitch range label and midi pitches

1

Hi there, First, thank you for putting together this dataset! I have a question regarding how the pitch range label is created. According to the paper: "We classify samples into...