Mask-Based Neural Beamforming for Moving Speakers With Self-Attention-Based Tracking.
Tsubasa OchiaiMarc DelcroixTomohiro NakataniShoko ArakiPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2023)
Keyphrases
- real time
- moving target
- neural network
- tracking multiple
- rigid objects
- kalman filter
- visual tracking
- network architecture
- continuously moving
- moving camera
- frequency domain
- particle filter
- motion analysis
- visual attention
- motion model
- neural model
- tracking objects
- associative memory
- bio inspired
- articulated objects
- speech recognition