Hierarchical representation and estimation of prosody using continuous wavelet transform

Research output: Contribution to journalArticle

Researchers

  • Antti Suni
  • Juraj Šimko
  • Daniel Aalto
  • Martti Vainio

Research units

  • University of Helsinki
  • Aalto University
  • University of Alberta
  • Misericordia Hospital

Abstract

Prominences and boundaries are the essential constituents of prosodic structure in speech. They provide for means to chunk the speech stream into linguistically relevant units by providing them with relative saliences and demarcating them within utterance structures. Prominences and boundaries have both been widely used in both basic research on prosody as well as in text-to-speech synthesis. However, there are no representation schemes that would provide for both estimating and modelling them in a unified fashion. Here we present an unsupervised unified account for estimating and representing prosodic prominences and boundaries using a scale-space analysis based on continuous wavelet transform. The methods are evaluated and compared to earlier work using the Boston University Radio News corpus. The results show that the proposed method is comparable with the best published supervised annotation methods.

Details

Original languageEnglish
Pages (from-to)123-136
Number of pages14
JournalComputer Speech and Language
Volume45
Publication statusPublished - 1 Sep 2017
MoE publication typeA1 Journal article-refereed

    Research areas

  • Phonetics, Prosody, Speech synthesis, Wavelets

ID: 15879038