Prosody structure prediction plays an important role in text-to-speech (TTS) conversion systems. It is the must and prior step to parametric prosody prediction. Dynamic programming (DP) and decision tree (DT) are widely used for prosody structure prediction [1][2][3] but with well-known limitations. In this paper, two other new methods, combination of dynamic programming with decision tree and combination of decision tree with finite state machine (FSM), are proposed. Then, based on a manually labeled corpus, comprehensive comparisons among the four methods are done. It could be concluded from these experiments that combination of dynamic programming with decision tree method is the best choice for prosody word boundary prediction and combination of decision tree with FSM is the best candidate for prosody phrase boundary prediction.
By: Qin Shi, Wei Zhang, XiJun Ma, WeiBin Zhu, Ling Jin
Published in: RC22917 in 2003
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 .