# Compression of Acoustic Event Detection Models With Quantized Distillation

## TL;DR

This paper introduces a combined knowledge distillation and quantization method to compress acoustic event detection models, significantly reducing model size and error rate for deployment on resource-constrained devices.

## Contribution

It presents a novel approach that jointly uses distillation and quantization to effectively compress AED models, improving accuracy and reducing size.

## Key findings

- Error rate of compact model reduced by 15% through distillation.
- Model size decreased to 2% of teacher model via quantization.
- Proposed method maintains high detection performance with smaller models.

## Abstract

Acoustic Event Detection (AED), aiming at detecting categories of events based on audio signals, has found application in many intelligent systems. Recently deep neural network significantly advances this field and reduces detection errors to a large scale. However how to efficiently execute deep models in AED has received much less attention. Meanwhile state-of-the-art AED models are based on large deep models, which are computational demanding and challenging to deploy on devices with constrained computational resources. In this paper, we present a simple yet effective compression approach which jointly leverages knowledge distillation and quantization to compress larger network (teacher model) into compact network (student model). Experimental results show proposed technique not only lowers error rate of original compact network by 15% through distillation but also further reduces its model size to a large extent (2% of teacher, 12% of full-precision student) through quantization.