ST ARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events
–Neural Information Processing Systems
Sound events in real sound scenes originate from their sound source objects, e.g., speech comes
Neural Information Processing Systems
Oct-9-2025, 10:19:19 GMT
- Genre:
- Research Report > New Finding (0.67)
- Industry:
- Government (0.67)
- Information Technology > Security & Privacy (1.00)
- Law (0.92)
- Leisure & Entertainment (0.94)
- Media > Music (0.68)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning
- Neural Networks > Deep Learning (0.68)
- Performance Analysis > Accuracy (0.68)
- Natural Language (0.67)
- Speech (0.68)
- Vision (0.70)
- Machine Learning
- Communications (1.00)
- Data Science (0.68)
- Security & Privacy (1.00)
- Artificial Intelligence
- Information Technology