The Community for Technology Leaders
Asian Language Processing, International Conference on (2009)
Dec. 7, 2009 to Dec. 9, 2009
ISBN: 978-0-7695-3904-1
pp: 34-38
While speech synthesis technologies have come a long way in recent ten years, there is still room for improvement. This paper describes a technique called based on joint information structure, syntax and prosody method, which demonstrates noticeable improvements to existing speech synthesis system. As an important parameter for prosody proceedings in mandarin, information focus prosodic distribution features are typical for hearing natural, speech understanding and in-formation acquisition. Because of the complex mapping relation between information structure, syntax and prosody, we present an efficient method for retrieval information focus to augment a naturalness speech synthesis. We use question answering chain to extract information focus and discover them how to move. Then, we adopt feature classification and prosody predictive modeling to deal with fo-cus’s F0 and time period and obtain them features module. Based on the features module, should significantly increase the accuracy and naturalness of speech synthesis. The rest of this paper is organized as follows. Section 2 summarizes the previously proposed theory for information focus extraction, and derives a new method. Experiments are expressed in Section 3. And experimental results are shown in Section 4. Concluding remarks are presented in the final section.
Information focus, Speech synthesis, Question answer chain
Jing Wan, Han Ren, "Information Focus Synthesis Based on Question Answer Chain", Asian Language Processing, International Conference on, vol. 00, no. , pp. 34-38, 2009, doi:10.1109/IALP.2009.16
93 ms
(Ver 3.3 (11022016))