Accent Group modeling for improved prosody in statistical parameteric speech synthesis

Gopala Krishna Anumanchipalli, Luís C. Oliveira, Alan W. Black

Abstract

This paper presents an `Accent Group' based intonation model for statistical parametric speech synthesis. We propose an approach to automatically model phonetic realizations of fundamental frequency(F0) contours as a sequence of intonational events anchored to a group of syllables (an Accent Group). We train an accent grouping model specific to that of the speaker, using a stochastic context free grammar and contextual decision trees on the syllables. This model is used to `parse' an unseen text into its constituent accent groups over each of which appropriate intonation is predicted. The performance of the model is shown objectively and subjectively on a variety of prosodically diverse tasks- read speech, news broadcast and audio books.
BibTeX
@inproceedings{anumanchipalli2013accent,
  author = {Gopala Krishna Anumanchipalli and Luís C. Oliveira and Alan W. Black},
  title = {{Accent Group modeling for improved prosody in statistical parameteric speech synthesis}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2013},
  doi = {10.1109/icassp.2013.6638997},
}

Loading related content...

Figure