Prosodic Events Recognition in Evaluation of Speech-Synthesis System Performance

  • Authors:
  • France Mihelič;Boštjan Vesnicer;Janez Žibert;Elmar Nöth

  • Affiliations:
  • Faculty od Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia SI-1000;Faculty od Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia SI-1000;Faculty od Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia SI-1000;University Erlangen-Nürnberg IMMD5, Erlangen, Germany 91058

  • Venue:
  • TSD '08 Proceedings of the 11th international conference on Text, Speech and Dialogue
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present an objective-evaluation method of the prosody modeling in an HMM-based Slovene speech-synthesis system. Method is based on the results of the automatic recognition of syntactic-prosodic boundary positions and accented words in the synthetic speech. We have shown that the recognition results represent a close match with the prosodic notations, labeled by the human expert on the natural-speech counterpart that was used to train the speech-synthesis system. The recognition rate of the prosodic events is proposed as an objective evaluation measure for the quality of the prosodic modeling in the speech-synthesis system. The results of the proposed evaluation method are also in accordance with previous subjective-listening assesment evaluations, where high scores for the naturalness for such a type of speech synthesis were observed.