Automated audio captioning with recurrent neural networks.
Konstantinos DrossosSharath AdavanneTuomas VirtanenPublished in: WASPAA (2017)
Keyphrases
- recurrent neural networks
- neural network
- echo state networks
- feed forward
- reservoir computing
- multimedia
- recurrent networks
- feedforward neural networks
- long short term memory
- complex valued
- semi automated
- artificial neural networks
- hebbian learning
- neural model
- nonlinear dynamic systems
- audio visual
- hidden layer
- cascade correlation
- real time
- audio signal
- audio stream