Speech-like Emotional Sound Generator by WaveNet

Kento Matsumoto, Sunao Hara, Masanobu Abe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a new algorithm to generate Speech-like Emotional Sound (SES). Emotional information plays an important role in human communication, and speech is one of the most useful media to express emotions. Although, in general, speech conveys emotional information as well as linguistic information, we have undertaken the challenge to generate sounds that convey emotional information without linguistic information, which results in making conversations in human-machine interactions more natural in some situations by providing non-verbal emotional vocalizations. We call the generated sounds 'speech-like', because the sounds do not contain any linguistic information. For the purpose, we propose to employ WaveNet as a sound generator conditioned by only emotional IDs. The idea is quite different from WaveNet Vocoder that synthesizes speech using spectrum information as auxiliary features. The biggest advantage of the idea is to reduce the amount of emotional speech data for the training. The proposed algorithm consists of two steps. In the first step, WaveNet is trained to obtain phonetic features using a large speech database, and in the second step, WaveNet is re-trained using a small amount of emotional speech. Subjective listening evaluations showed that the SES could convey emotional information and was judged to sound like a human voice.

Original languageEnglish
Title of host publication2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages143-147
Number of pages5
ISBN (Electronic)9781728132488
DOIs
Publication statusPublished - Nov 2019
Event2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019 - Lanzhou, China
Duration: Nov 18 2019Nov 21 2019

Publication series

Name2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019

Conference

Conference2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
CountryChina
CityLanzhou
Period11/18/1911/21/19

ASJC Scopus subject areas

  • Information Systems

Fingerprint Dive into the research topics of 'Speech-like Emotional Sound Generator by WaveNet'. Together they form a unique fingerprint.

Cite this