Environment Transfer for Distributed Systems

TL;DR

This paper introduces a novel environment transfer technique for augmenting distributed acoustic data by transferring environmental signatures between audio samples, improving data diversity for machine learning tasks.

Contribution

It extends existing style transfer methods to transfer environmental signatures in audio, with new metrics for evaluating environmental transfer quality.

Findings

Enhanced classification accuracy with transferred environmental features

Better preservation of content features in augmented data

Effective transfer of environmental signatures demonstrated on UrbanSound8K

Abstract

Collecting sufficient amount of data that can represent various acoustic environmental attributes is a critical problem for distributed acoustic machine learning. Several audio data augmentation techniques have been introduced to address this problem but they tend to remain in simple manipulation of existing data and are insufficient to cover the variability of the environments. We propose a method to extend a technique that has been used for transferring acoustic style textures between audio data. The method transfers audio signatures between environments for distributed acoustic data augmentation. This paper devises metrics to evaluate the generated acoustic data, based on classification accuracy and content preservation. A series of experiments were conducted using UrbanSound8K dataset and the results show that the proposed method generates better audio data with transferred environmental features while preserving content features.