SAGRNN: Self-Attentive Gated RNN For Binaural Speaker Separation With Interaural Cue Preservation.
Ke TanBuye XuAnurag KumarEliya NachmaniYossi AdiPublished in: IEEE Signal Process. Lett. (2021)
Keyphrases
- sound source
- audio visual
- recurrent neural networks
- focus of attention
- visual motion
- speech signal
- multi modal
- speech recognition
- nearest neighbor
- speaker verification
- speaker identification
- visual information
- automatic speech recognition
- visual attention
- visual data
- speaker recognition
- multimedia
- visual cues
- speaker dependent
- prosodic features
- data sets
- high dimensional
- image sequences
- genetic algorithm
- neural network
- real environment
- digital objects
- hidden markov models
- artificial neural networks
- pre attentive