EURASIP Journal on Audio, Speech, and Music Processing

Table 3 Distribution of speech and music events over the 77,936 AUDIAS-balanced—June 2018 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	27.69	24.10	51.79
Speech	24.10	24.10	48.21
Total	51.79	48.21	100

Back to article page