UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures
–Neural Information Processing Systems
In reverberant conditions with multiple concurrent speakers, each microphone acquires a mixture signal of multiple speakers at a different location.
Neural Information Processing Systems
Oct-8-2025, 20:38:35 GMT
- Country:
- Asia > India (0.04)
- North America > United States
- Illinois (0.04)
- Genre:
- Research Report (0.46)
- Technology: