HMM-based expressive speech synthesis based on phrase-level F0 context labeling

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

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

3 Citations (Scopus)

Abstract

This paper proposes a technique for adding more prosodic variations to the synthetic speech in HMM-based expressive speech synthesis. We create novel phrase-level F0 context labels from the residual information of F0 features between original and synthetic speech for the training data. Specifically, we classify the difference of average log F0 values between the original and synthetic speech into three classes which have perceptual meanings, i.e., high, neutral, and low of relative pitch at the phrase level. We evaluate both ideal and practical cases using appealing and fairy tale speech recorded under a realistic condition. In the ideal case, we examine the potential of our technique to modify the F0 patterns under a condition where the original F0 contours of test sentences are known. In the practical case, we show how the users intuitively modify the pitch by changing the initial F0 context labels obtained from the input text.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Pages7859-7863
Number of pages5
DOIs
Publication statusPublished - 2013 Oct 18
Externally publishedYes
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: 2013 May 262013 May 31

Publication series

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

Other

Other2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
CountryCanada
CityVancouver, BC
Period13/5/2613/5/31

Keywords

  • HMM-based expressive speech synthesis
  • audiobook
  • prosodic context
  • prosody control
  • unsupervised labeling

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'HMM-based expressive speech synthesis based on phrase-level F0 context labeling'. Together they form a unique fingerprint.

  • Cite this

    Maeno, Y., Nose, T., Kobayashi, T., Koriyama, T., Ijima, Y., Nakajima, H., Mizuno, H., & Yoshioka, O. (2013). HMM-based expressive speech synthesis based on phrase-level F0 context labeling. In 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings (pp. 7859-7863). [6639194] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2013.6639194