Visual onoma-to-wave: environmental sound synthesis from visual onomatopoeias and sound-source images

TL;DR

This paper introduces a novel method for synthesizing environmental sounds from visual onomatopoeias and sound-source images, leveraging visual text representations to produce diverse and realistic sounds.

Contribution

It proposes a new approach called visual onoma-to-wave that uses visual onomatopoeias and images, along with data augmentation, to improve environmental sound synthesis.

Findings

Effective synthesis of diverse environmental sounds from visual inputs.

Visual onomatopoeias contain rich information for sound diversity.

Data augmentation enhances synthesis performance.

Abstract

We propose a method for synthesizing environmental sounds from visually represented onomatopoeias and sound sources. An onomatopoeia is a word that imitates a sound structure, i.e., the text representation of sound. From this perspective, onoma-to-wave has been proposed to synthesize environmental sounds from the desired onomatopoeia texts. Onomatopoeias have another representation: visual-text representations of sounds in comics, advertisements, and virtual reality. A visual onomatopoeia (visual text of onomatopoeia) contains rich information that is not present in the text, such as a long-short duration of the image, so the use of this representation is expected to synthesize diverse sounds. Therefore, we propose visual onoma-to-wave for environmental sound synthesis from visual onomatopoeia. The method can transfer visual concepts of the visual text and sound-source image to the synthesized sound. We also propose a data augmentation method focusing on the repetition of onomatopoeias to enhance the performance of our method. An experimental evaluation shows that the methods can synthesize diverse environmental sounds from visual text and sound-source images.