Overlapping Speech Error Rates: Use 1—ASR Word Error Rate, Not Diarization

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).

Learn why 1—ASR should be chosen by WER on representative overlapped audio, and why overlap-aware DER must evaluate diarization separately from WER. Independent technical note mirroring the canonical version: https://transcribeall.io/blog/overlapping-speech-error-rates-use-1asr-word-error-rate-not-diarization.php