MIMO Self-attentive RNN Beamformer for Multi-speaker Speech Separation.
Xiyun LiYong XuMeng YuShi-Xiong ZhangJiaming XuBo XuDong YuPublished in: CoRR (2021)
Keyphrases
- speech recognition
- audio visual
- speaker recognition
- automatic speech recognition
- speaker verification
- speaker identification
- recurrent neural networks
- speech signal
- nearest neighbor
- speaker dependent
- multipath
- automatic transcription
- prosodic features
- vocal tract
- speaker diarization
- signal to noise ratio
- minimum variance
- speech sounds
- automatic speech recognition systems
- dialogue system
- linear prediction
- emotion recognition
- speaker independent
- noisy environments
- focus of attention
- visual attention
- hidden markov models