Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network.
Xiaolin HuKai LiWeiyi ZhangYi LuoJean-Marie LemercierTimo GerkmannPublished in: CoRR (2021)
Keyphrases
- convolutional neural network
- face detection
- speech recognition
- recurrent neural networks
- speech signal
- neural network
- multi stream
- automatic speech recognition
- feed forward
- speaker recognition
- state machines
- recognition engine
- face recognition
- data sets
- audio visual
- pattern recognition
- multi class
- emotion recognition
- spoken language
- support vector machine
- hidden markov models