I’m Sorry for Your Loss: Spectrally-Based Audio Distances Are Bad at Pitch
Abstract
Growing research demonstrates that synthetic failure modes imply poor generalization. We compare commonly used audio-to-audio losses on a synthetic benchmark, measuring the pitch distance between two stationary sinusoids. The results are surprising: many have poor sense of pitch direction. These shortcomings are exposed using simple rank assumptions. Our task is trivial for humans but difficult for these audio distances, suggesting significant progress can be made in self-supervised audio learning by improving current losses.
Cite
Text
Turian and Henry. "I’m Sorry for Your Loss: Spectrally-Based Audio Distances Are Bad at Pitch." NeurIPS 2020 Workshops: ICBINB, 2020.Markdown
[Turian and Henry. "I’m Sorry for Your Loss: Spectrally-Based Audio Distances Are Bad at Pitch." NeurIPS 2020 Workshops: ICBINB, 2020.](https://mlanthology.org/neuripsw/2020/turian2020neuripsw-im/)BibTeX
@inproceedings{turian2020neuripsw-im,
title = {{I’m Sorry for Your Loss: Spectrally-Based Audio Distances Are Bad at Pitch}},
author = {Turian, Joseph and Henry, Max},
booktitle = {NeurIPS 2020 Workshops: ICBINB},
year = {2020},
url = {https://mlanthology.org/neuripsw/2020/turian2020neuripsw-im/}
}