EURASIP Journal on Audio, Speech, and Music Processing

Table 2 Distribution of speech and music events over the unbalanced train segments

From: Exploring convolutional, recurrent, and hybrid deep neural networks for speech and music detection in a large audio dataset

	No-music (%)	Music (%)	Total (%)
No-speech	17.30	33.50	50.80
Speech	33.76	15.44	49.20
Total	51.06	48.94	100

Back to article page