Knowledge Distillation for Real-Time Classification of Early Media in Voice Communications

October 28, 2024 ยท Declared Dead ยท ๐Ÿ› IEEE/ACM International Symposium on Modeling, Analysis, and Simulation On Computer and Telecommunication Systems

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Kemal Altwlkany, Hadลพem Hadลพiฤ‡, Amar Kuriฤ‡, Emanuel Lacic arXiv ID 2410.21478 Category cs.SD: Sound Cross-listed cs.AI, cs.MM, eess.AS Citations 1 Venue IEEE/ACM International Symposium on Modeling, Analysis, and Simulation On Computer and Telecommunication Systems Last Checked 4 months ago
Abstract
This paper investigates the industrial setting of real-time classification of early media exchanged during the initialization phase of voice calls. We explore the application of state-of-the-art audio tagging models and highlight some limitations when applied to the classification of early media. While most existing approaches leverage convolutional neural networks, we propose a novel approach for low-resource requirements based on gradient-boosted trees. Our approach not only demonstrates a substantial improvement in runtime performance, but also exhibits a comparable accuracy. We show that leveraging knowledge distillation and class aggregation techniques to train a simpler and smaller model accelerates the classification of early media in voice calls. We provide a detailed analysis of the results on a proprietary and publicly available dataset, regarding accuracy and runtime performance. We additionally report a case study of the achieved performance improvements at a regional data center in India.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Sound

Died the same way โ€” ๐Ÿ‘ป Ghosted