EURASIP Journal on Audio, Speech, and Music Processing

Table 8 Mean error rates of pitch detection methods (italics indicates the best results for the mean performance)

From: A computational study of auditory models in music recognition tasks for normal-hearing and hearing-impaired listeners

	Polyphonic/predominant				Mono.
Method	Cello	Clar.	Trump.	Mean	Mean
SACF max.	0.55	0.52	0.54	0.54	0.20
SACF thresh.	0.24	0.12	0.17	0.18	0.05
DFT + RF	0.14	0.02	0.08	0.08	0.02
DFT + SVM	0.11	0.01	0.08	0.07	0.02
ACF + RF	0.24	0.08	0.30	0.20	0.05
ACF + SVM	0.21	0.05	0.24	0.17	0.04
YIN + aperiodic power	0.36	0.15	0.32	0.28	0.05
YIN + median	0.04	0.01	0.04	0.03	0.00
YIN + 10% quantile	0.11	0.04	0.09	0.08	0.03
pYIN + median	0.04	0.17	0.07	0.09	0.12
pYIN + 10% quantile	0.04	0.10	0.01	0.05	0.04

Back to article page