Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network.
Xiaolin HuKai LiWeiyi ZhangYi LuoJean-Marie LemercierTimo GerkmannPublished in: NeurIPS (2021)
Keyphrases
- convolutional neural network
- face detection
- speech recognition
- speech signal
- neural network
- recurrent neural networks
- dialogue system
- speech synthesis
- feature extraction
- endpoint detection
- feed forward
- spoken language
- multi unit combinatorial auctions
- text to speech synthesis
- speaker identification
- text to speech
- asynchronous circuits
- multi stream
- asynchronous communication
- recognition engine
- artificial neural networks
- audio stream
- natural language
- genetic algorithm
- machine learning