I don’t like self promotion but I really recommend this review paper on synthetic speech evaluation, mostly written by @erica_cooper (I contributed partly as well)
https://t.co/0mqmEYftIF
And really hope people understand there is just no good evaluation metric like human ears
Henry Li, Robin Scheibler, Efthymios Tzinis, Matt Shannon, Arnaud Doucet, John R. Hershey, "SURF: Separation via Unsupervised Remixing Flow," https://t.co/kStyuxYxJt
Shrishti Saha Shetu, Emanu\"el A. P. Habets, Andreas Brendel, "A Comparison of Generative and Discriminative Methods for Speech Enhancement: Robustness, Complexity, and Hallucination," https://t.co/PCFpcAVDi3
Our paper is now available on arXiv!
We propose a new spotforming method that utilizes non-target estimates across microphone arrays without relying on low-rank approximations.
https://t.co/HwHFIJ2bFk