# Fast computation of loudness using a deep neural network

## TL;DR

This paper presents a deep neural network that predicts instantaneous loudness from sound waveforms, achieving real-time performance with high accuracy by approximating a complex loudness model.

## Contribution

The authors develop a DNN that accurately and rapidly predicts loudness, enabling real-time applications and demonstrating the potential of neural networks to simulate complex perceptual models.

## Key findings

- DNN predicts loudness with less than 0.5 phon deviation.
- DNN performs over 100,000 computations per second.
- Approach can be applied to other perceptual models.

## Abstract

The present paper introduces a deep neural network (DNN) for predicting the instantaneous loudness of a sound from its time waveform. The DNN was trained using the output of a more complex model, called the Cambridge loudness model. While a modern PC can perform a few hundred loudness computations per second using the Cambridge loudness model, it can perform more than 100,000 per second using the DNN, allowing real-time calculation of loudness. The root-mean-square deviation between the predictions of instantaneous loudness level using the two models was less than 0.5 phon for unseen types of sound. We think that the general approach of simulating a complex perceptual model by a much faster DNN can be applied to other perceptual models to make them run in real time.