SALSA
SALSA copied to clipboard
thomeou
This is the public repository for eigenvector-based SALSA features for polyphonic sound event localization and detection.
Hi, i have a problem about how to calculate the salsa-lite. What is the meaning of "arg" in your paper. Here is the link to the formula picture. https://github.com/kakarotto007/typora/blob/main/Snipaste_2023-04-25_15-13-16.png @karnwatcharasupat...
Hello, i have a question about how to calculate phase_vector. Why "phase_vector = np.angle(X[:, :, 1:] * np.conj(X[:, :, 0, None]))" ? Thank you very much!
@andres-fr #20 Dear Andre, I have recorded a 4-channel sound file with this array: https://wiki.seeedstudio.com/ReSpeaker-USB-Mic-Array/ but the SALSA-code does not localize sounds and the results are completely wrong. Can you...
I am working on sound source localization. I have read your papers entitled: "Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection" and "A Fast and Effective Feature...
Hello, thank you very much for sharing such excellent work with us I have done similar work recently, but I have encountered difficulties in model visualization. I want to know...
Hello: What a incredible project，but I have a question . Does it support the SELD of overlap sound of the same classe?
Hi. Thank you all for this amazing work and sharing it with us. I was going through your code to understand how you're doing data augmentation, specifically channel swapping, and...
Hi Thank you for this sharing your work. Will it be possible to share the trained models?
The `load_chunk_data` method is aggressively cosuming huge amounts of RAM when concatenating np arrays. I am currently trying to implement something that will reduce the RAM consumption @karnwatcharasupat @thomeou I...
