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

arXiv: https://arxiv.org/abs/2410.21478 · HTML: https://mlsanity.com/paper/2410.21478/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 2 of its 15 references that are in the map.
- First posted on arXiv 28 Oct 2024.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

## Builds on (most cited first, 2 of 2)

- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [Automatic tagging using deep convolutional neural networks](https://mlsanity.com/paper/1606.00298/) (2016)

## Built on by (most cited first, 1 of 1)

- [Pretrained Conformers for Audio Fingerprinting and Retrieval](https://mlsanity.com/paper/2508.11609/) (2025)

## Abstract (arXiv)

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.