Generalized Spatio-Temporal RNN Beamformer for Target Speech Separation.
Yong XuZhuohuang ZhangMeng YuShi-Xiong ZhangDong YuPublished in: Interspeech (2021)
Keyphrases
- spatio temporal
- recurrent neural networks
- speech recognition
- spatial and temporal
- nearest neighbor
- image sequences
- signal to noise ratio
- multipath
- neural network
- data sets
- automatic speech recognition
- speech synthesis
- spatial temporal
- target tracking
- moving objects
- feed forward
- human actions
- target object
- end to end
- audio visual
- multi modal
- pattern recognition
- spatio temporal data
- broadcast news
- speaker recognition
- computer vision