HMM-based emphatic speech synthesis using unsupervised context labeling

Yu Maeno, Takashi Nose, Takao Kobayashi, Yusuke Ijima, Hideharu Nakajima, Hideyuki Mizuno, Osamu Yoshioka

Research output: Contribution to journalConference articlepeer-review

16 Citations (Scopus)

Abstract

This paper describes an approach to HMM-based expressive speech synthesis which does not require any supervised labeling process for emphasis context. We use appealing-style speech whose sentences were taken from real domains. To reduce the cost for labeling speech data with an emphasis context for the model training, we propose an unsupervised labeling technique of the emphasis context based on the difference between original and generated F0 patterns of training sentences. Although the criterion for the emphasis labeling is quite simple, subjective evaluation results reveal that the unsupervised labeling is comparable to the labeling conducted carefully by a human in terms of speech naturalness and emphasis reproducibility.

Original languageEnglish
Pages (from-to)1849-1852
Number of pages4
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - 2011 Dec 1
Externally publishedYes
Event12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 - Florence, Italy
Duration: 2011 Aug 272011 Aug 31

Keywords

  • Emphasis expression
  • Expressive speech
  • F0 generation
  • HMM-based speech synthesis
  • Unsupervised labeling

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'HMM-based emphatic speech synthesis using unsupervised context labeling'. Together they form a unique fingerprint.

Cite this