Voorspellen audiomaten fouten van de spraakherkenner?

Dit is de beschrijving van de toets zoals die in de status van de SNR-maat op /lenses staat. We tonen hem woord voor woord (in het Engels, zoals hij in het register staat), zodat deze pagina niet meer kan zeggen dan de status.

Predicting speech-recognition errors: in our own test of 10 October 2026: 16 invented Dutch citizen reports (street and number, town, surname, phone, email), read by 3 synthetic voices in 13 conditions (clean, telephone band, street noise and babble at 10 and 5 dB, television, four measured reverberation times, combinations): 624 recordings, 1,248 transcriptions by Whisper small and large-v3-turbo, 48 per condition and model, margin about 13 points. It did not predict errors in street, number and town (AUC 0.52 to 0.55; 0.50 is a coin flip). Synthetic voices, Whisper only, simulated telephone band, Dutch text; real speakers, other recognisers and languages are untested.