Dylan Cooper · Zenodo (CERN European Organization for Nuclear Research) 2026 · 2026
DOI: 10.5281/zenodo.22978683
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).
A 5 dB cafe clip drops cloned voice similarity to 0.61 and MOS to 3.18, while 20 dB holds 0.82 and 4.21. Learn when to denoise or re-record. Independent technical note mirroring the canonical version: https://clonemyvoice.io/blog/voice-cloning-audio-quality-5-db-vs-20-db-denoise-or-re-record.php
No comments yet — start the discussion below.