CITATION — REFERENCE ENTRY

si-snr · luo2019-conv-tasnet

Revision 87ca351f-dbb4-4ac7-a1bc-25e2f4e5d0c5 · 11/21/2026, 6:51:30 AM UTC
Claim ID
si-snr
Assertion
Conv-TasNet is trained to maximize the scale-invariant source-to-noise ratio (SI-SNR).
Quote
The objective of training the end-to-end system is maximizing the scale-invariant source-to-noise ratio (SI-SNR), which has commonly been used as the evaluation metric for source separation replacing the standard source-to-distortion ratio (SDR)
Quote language
en
Locator
page: 5 (sec. III.C)
Available in