Is there one best AI dialogue cleaner for noise and reverb, according to a published blind listening test?

Problem: choosing a noise or reverb reduction tool for production dialogue. Conditions: two Production Expert blind listening polls (noise reduction; reverb reduction), randomised processed versions, listeners voted for the most effective per clip; the reverb part used deliberately extreme examples and few clips. Method: read per-clip winners, not the aggregate. Measured result (vote shares, n of voters not stated on the page): noise test, dxRevive Pro won one clip with over 50 percent of votes, Hush Pro won broadband noise with 64.32 percent, hum was a near three-way draw (Extract: Dialogue, RX Dialogue Isolate, dxRevive Pro), roadside traffic went to Hush Pro with 38 percent; reverb test, Hush Pro led 3 of 4 clips (34.07, 53.49, 55.05 percent) and dxRevive Pro led one (40 percent vs 37.91). Failure modes: results depend on clip choice; Hush Pro came last on the hum clip. Limitations: number of listeners and clips is small, not peer reviewed, early versions of tools. Version/date: pages undated; the tests predate current versions. Inference: test per clip type and keep more than one tool. Curator qualifications: All cited documentation excerpts located on the live pages by curator GET; no video sources. Correction folded 2026-10-24 from C3-B724-02 (curator-reviewed discovery audit): Problem. C3-B700-04 says the number of voters is not stated and calls the number of listeners small. Correction. The noise-reduction results page reports total votes per plug-in across all four tests (685, 636, 369, 249, 198 and 191, about 2,328 votes in total). The page does not state how many distinct listeners voted, so listener count is unknown rather than shown to be small. The page also says nothing about tool versions being early or the tests predating current versions, so that caveat is the original author's inference. Per-clip winners and the conclusion that no single plug-in wins everything are as the original states. Limitations. Vote totals count votes across clips, not people; an informal poll, not peer reviewed. Version/date. Page undated. Limitations: No listener n, no confidence intervals, vendor trial links on the page; results snapshot is from an earlier tool generation. Corrected by C3-B724-02; where the correction disagrees, the correction governs. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://www.production-expert.com/production-expert-1/results-dialogue-restoration-listening-test-noise-reduction",
      "note": "noise test conclusion; test one; reverb conclusion; reverb caveat; researcher reasoning"
    },
    {
      "url": "https://www.production-expert.com/production-expert-1/dialogue-restoration-listening-test-reverb-reduction-the-results",
      "note": "noise test conclusion; test one; reverb conclusion; reverb caveat; researcher reasoning"
    }
  ]
}