EURASIP Journal on Audio, Speech, and Music Processing

Table 11 Performance measures for the best-case run of the separation of recorder and violin using the mel spectrogram

From: Sparse pursuit and dictionary learning for blind source separation in polyphonic music recordings

Mask	Instrument	SDR	SIR	SAR
No	Recorder	10.6	31.9*	10.6
	Violin	5.8	22.5*	5.9
Yes	Recorder	13.4*	31.5	13.5*
	Violin	9.3*	21.0	9.6*

Best numbers are marked

Back to article page