A low-latency, real-time-capable singing voice detection method with LSTM recurrent neural networks.
Bernhard LehnerGerhard WidmerSebastian BöckPublished in: EUSIPCO (2015)
Keyphrases
- recurrent neural networks
- detection method
- low latency
- real time
- long short term memory
- high speed
- high bandwidth
- high throughput
- detection algorithm
- face detection
- neural network
- feed forward
- recurrent networks
- virtual machine
- reservoir computing
- artificial neural networks
- highly efficient
- echo state networks
- stream processing
- computer vision
- region detection
- data management
- data distribution
- nonlinear dynamic systems