Table 2. Number of labels and syllables of dataset 2 and 3.

ID	# labels	Dataset 2, # samples for training					Dataset 3 # syllables
		120 s	90 s	60 s	30 s	15 s
b01	14	690	507	326	137	46	8610
b06	8	724	548	358	163	70	10750
b09	9	885	637	430	215	112	13129
b10	10	796	604	399	207	101	18767
b11	7	851	648	434	219	105	11580
b13	10	799	607	402	203	99	64825
b14	8	821	620	406	191	84	40836
b16	7	798	598	399	200	100	28633
b17	8	779	592	393	203	107	49013
b18	8	763	578	383	186	91	17399
b19	5	764	580	387	192	97	28893
b20	9	636	498	327	157	74	8581
b21	9	774	594	393	181	80	37709
mean	8.6	773.1	585.5	387.5	188.8	89.7	26055.8
SD	2.1	61.4	44.8	33.1	24.0	18.4	17672.3
Mean syllables/label	-	89.7	68.0	45.0	21.9	10.4	3024.3