Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
Speech deepfake detectors consume decoded waveforms, but for coded speech the bitstream is what was transmitted; which rendering of it the detector sees belongs to the receiver. Decoding a bit-identical Opus bitstream with libopus 1.6.1’s stronger optional decoder-side post-filter enabled rather than disabled shifts class-mean detector scores toward the synthetic class in 20 of 20 detector–class–corpus cells, with no packet loss and no change to a transmitted byte. At a threshold transferred from the unenhanced rendering at a 1% false-alarm target, false alarms rise in all eight cells; one public detector goes from 1.00% to 3.80% while its equal-error rate moves only from 0.30% to 0.40%. The shift is not a monotone rescaling that recalibration absorbs: items cross the threshold in both directions, and equal-error rate moves in every cell. On held-out data a stale threshold multiplies false alarms by 1.7 to 3.8. Refitting recovers the target rate, but no corpus, protocol or file header records that the configuration changed. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.
No comments yet — start the discussion below.