An End-to-End Audio Classification System Based on Raw Waveforms and Mix-Training Strategy.
Jiaxu ChenJing HaoKai ChenDi XieShicai YangShiliang PuPublished in: INTERSPEECH (2019)
Keyphrases
- end to end
- training set
- training samples
- text localization and recognition
- congestion control
- wireless ad hoc networks
- supervised learning
- feature vectors
- high bandwidth
- ad hoc networks
- real world
- rate allocation
- admission control
- scalable video
- multimedia
- multi hop
- video sequences
- internet protocol
- rate adaptation
- transport layer