Determination of representative emotional style of speech based on k-means algorithm

Sangshin Oh, Se Yun Um, Inseon Jang, Chung Hyun Ahn, Hong Goo Kang

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we propose a method to effectively determine the representative style embedding of each emotion class to improve the global style token-based end-to-end speech synthesis system. The emotion expressiveness of conventional approach was limited because it utilized only one style representative per each emotion. We overcome the problem by extracting multiple number of representatives per each emotion using a k-means clustering algorithm. Through the results of listening tests, it is proved that the proposed method clearly express each emotion while distinguishing one emotion from others.

Original languageEnglish
Pages (from-to)614-620
Number of pages7
JournalJournal of the Acoustical Society of Korea
Volume38
Issue number5
DOIs
Publication statusPublished - 2019

Bibliographical note

Publisher Copyright:
© 2019 Acoustical Society of Korea. All rights reserved.

All Science Journal Classification (ASJC) codes

  • Acoustics and Ultrasonics
  • Instrumentation
  • Applied Mathematics
  • Signal Processing
  • Speech and Hearing

Fingerprint

Dive into the research topics of 'Determination of representative emotional style of speech based on k-means algorithm'. Together they form a unique fingerprint.

Cite this