CNNs generalize better than dense networks on noisy user labels for VoIP audio impairment classification, with larger datasets needed in proportion to noise level.
Engineered audio features with dense network In the first approach, we extract 18 engineered signal processing features from the audio signal
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Supervised Classifiers for Audio Impairments with Noisy Labels
CNNs generalize better than dense networks on noisy user labels for VoIP audio impairment classification, with larger datasets needed in proportion to noise level.