Overview of Tasks and Investigation of Subjective Evaluation Methods in Environmental Sound Synthesis and Conversion

TL;DR

This paper reviews environmental sound synthesis and conversion, focusing on problem definitions, applications, evaluation methods, and the current state of statistical models, while also exploring subjective evaluation techniques.

Contribution

It provides a comprehensive overview of the field and investigates the effectiveness of subjective evaluation methods for statistical environmental sound synthesis.

Findings

Current performance of statistical sound synthesis methods

Insights into conducting subjective experiments

Identification of research gaps in environmental sound conversion

Abstract

Synthesizing and converting environmental sounds have the potential for many applications such as supporting movie and game production, data augmentation for sound event detection and scene classification. Conventional works on synthesizing and converting environmental sounds are based on a physical modeling or concatenative approach. However, there are a limited number of works that have addressed environmental sound synthesis and conversion with statistical generative models; thus, this research area is not yet well organized. In this paper, we review problem definitions, applications, and evaluation methods of environmental sound synthesis and conversion. We then report on environmental sound synthesis using sound event labels, in which we focus on the current performance of statistical environmental sound synthesis and investigate how we should conduct subjective experiments on environmental sound synthesis.