EMOQ-TTS: EMOTION INTENSITY QUANTIZATION FOR FINE-GRAINED CONTROLLABLE EMOTIONAL TEXT-TO-SPEECH

Chae Bin Im, Sang Hoon Lee, Seung Bin Kim, Seong Whan Lee

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

Abstract

Although recent advances in text-to-speech (TTS) have shown significant improvement, it is still limited to emotional speech synthesis. To produce emotional speech, most works utilize emotion information extracted from emotion labels or reference audio. However, they result in monotonous emotional expression due to the utterance-level emotion conditions. In this paper, we propose EmoQ-TTS, which synthesizes expressive emotional speech by conditioning phoneme-wise emotion information with fine-grained emotion intensity. Here, the intensity of emotion information is rendered by distance-based intensity quantization without human labeling. We can also control the emotional expression of synthesized speech by conditioning intensity labels manually. The experimental results demonstrate the superiority of EmoQ-TTS in emotional expressiveness and controllability.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6317-6321
Number of pages5
ISBN (Electronic)9781665405409
DOIs
Publication statusPublished - 2022
Event47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore
Duration: 2022 May 232022 May 27

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityVirtual, Online
Period22/5/2322/5/27

Keywords

  • Text-to-speech
  • emotion intensity modeling
  • expressive emotional speech synthesis
  • fine-grained control

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'EMOQ-TTS: EMOTION INTENSITY QUANTIZATION FOR FINE-GRAINED CONTROLLABLE EMOTIONAL TEXT-TO-SPEECH'. Together they form a unique fingerprint.

Cite this