We analyze the distribution of ToBI labels in a corpus collected from a professional speaker for use in concatenative speech synthesis. Our goals include using such statistics to aid automatic ToBI labeling of such a corpus, analogously to how a language model aids speech recognition. We find that the professional speaker produces a rich variety of prosodic events. ToBI labels occur with skewed frequencies, with a trigram model for occurrences of 34 ToBI labels yielding a perplexity of 3.23, indicating that such statistics will likely aid recognition of those prosodic categories. We relate ToBI label occurrence to sentence type and word frequency, determining patterns which confirm that text information would also useful to such a recognizer.
By: John F. Pitrelli
Published in: RC23086 in 2004
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .