APSIPA Transactions on Signal and Information Processing > Vol 11 > Issue 1

Onoma-to-wave: Environmental Sound Synthesis from Onomatopoeic Words

Yuki Okamoto, Ritsumeikan University, Japan, y-okamoto@ieee.org , Keisuke Imoto, Doshisha University, Japan, Shinnosuke Takamichi, The University of Tokyo, Japan, Ryosuke Yamanishi, Kansai University, Japan, Takahiro Fukumori, Ritsumeikan University, Japan, Yoichi Yamashita, Ritsumeikan University, Japan
 
Suggested Citation
Yuki Okamoto, Keisuke Imoto, Shinnosuke Takamichi, Ryosuke Yamanishi, Takahiro Fukumori and Yoichi Yamashita (2022), "Onoma-to-wave: Environmental Sound Synthesis from Onomatopoeic Words", APSIPA Transactions on Signal and Information Processing: Vol. 11: No. 1, e13. http://dx.doi.org/10.1561/116.00000049

Publication Date: 23 May 2022
© 2022 Y. Okamoto, K. Imoto, S. Takamichi, R. Yamanishi, T. Fukumori and Y. Yamashita
 
Subjects
 
Keywords
Environmental sound synthesissound eventonomatopoeic wordsequence-to-sequence model
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 453 times

In this article:
Introduction 
Proposed Method 
Experiments 
Conclusion 
References 

Abstract

In this paper, we propose a framework for environmental sound synthesis from onomatopoeic words. As one way of expressing an environmental sound, we can use an onomatopoeic word, which is a character sequence for phonetically imitating a sound. An onomatopoeic word is effective for describing diverse sound features. Therefore, the use of onomatopoeic words as input for environmental sound synthesis will enable us to generate diverse sounds. To generate diverse sounds, we propose a method based on a sequence-to-sequence framework for synthesizing environmental sounds from onomatopoeic words. We also propose a method of environmental sound synthesis using onomatopoeic words and sound event labels. The use of sound event labels in addition to onomatopoeic words enables us to capture each sound event’s feature depending on the input sound event label. Our subjective experiments show that our proposed methods achieve higher diversity and naturalness than conventional methods using sound event labels.

DOI:10.1561/116.00000049