Effectiveness of Speech Mode Adaptation for Improving Dialogue Speech Synthesis

• KAYA Kazuki

  Graduate School of Engineering, Utsunomiya University

• MORI Hiroki

  Graduate School of Engineering, Utsunomiya University

Abstract

The effectiveness of model adaptation in dialogue speech synthesis is explored. The proposed adaptation method is based on a conversion from a base model learned with a large dataset into a target, dialogue-style speech model. The proposed method is shown to improve the intelligibility of synthesized dialogue speech, while maintaining the speaking style of dialogue.

Journal

• IEICE Transactions on Information and Systems

  IEICE Transactions on Information and Systems E102.D (10), 2064-2066, 2019-10-01

  The Institute of Electronics, Information and Communication Engineers

Keywords

• dialogue
• speech synthesis
• HMM
• transfer learning

Details

• CRID: 1390001277363764864
• NII Article ID: 130007722181
• DOI: 10.1587/transinf.2019edl8024
• ISSN: 17451361
• ISSN: 09168532
• Web Site: https://www.jstage.jst.go.jp/article/transinf/E102.D/10/E102.D_2019EDL8024/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed