====================================================================== CALL FOR PAPERS IEEE Journal of Selected Topics in Signal Processing Special Issue on Statistical Parametric Speech Synthesis Statistical parametric speech synthesizers have recently shown their ability to produce natural-sounding and flexible voices. It only needs a small training database that can be easily prepared, and the system can be easily adapted to a new voice. Although the statistical parametric speech synthesizer has been certainly successful, there is still a lot of challenge for that. For instance, a) how to build a statistical parametric speech synthesizer that can generate emotional or expressive speech, and how to use it in natural dialog applications; b) is it possible to combine physical speech production models for statistical parametric speech synthesis to improve the speech quality; c) how to build high quality statistical parametric speech synthesizers by only using a very small training database; d) how to build parametric synthesizers or speaker adaptation models for cross-language or multi-language. The purpose of this special issue is to present recent advances on statistical parametric speech synthesis, and try to find the better solution to improve the naturalness and expressivity of the synthesis results and new areas to extend the features/applications of statistical parametric speech synthesis. Contributed papers are invited on, but are not limited to, the following topics: - Methods for expressive statistical parametric speech synthesis - Crosslingual/multilingual techniques for statistical parametric speech synthesis - New speech generation/excitation models for statistical parametric speech - Combination with physical speech production models for statistical parametric speech synthesis - Statistical parametric speech synthesis for low-resource languages - New character adaptation method for statistical parametric speech synthesis - New applications for statistical parametric speech synthesis, especially in games, education or medical applications Prospective authors should visit http://www.signalprocessingsociety.org/publications/periodicals/jstsp/ for information on paper submission. Manuscripts should be submitted using the Manuscript Central system at http://mc.manuscriptcentral.com/jstsp-ieee. Manuscripts will be peer reviewed according to the standard IEEE process. Proposed Schedule: Submission deadline: March 10, 2013 First review completed: June 10, 2013 Revised manuscript due: July 10, 2013 Second review completed: Sept 10, 2013 Final manuscript due: Oct 1, 2013 Guest Editors: Jianhua Tao jhtao@xxxxxxxxxxxxx (Chinese Academy of Sciences, China) Keikichi Hirose hirose@xxxxxxxxxxxxxxxxxxxx (University of Tokyo, Japan) Keiichi Tokuda tokuda@xxxxxxxxxxxx (Nagoya Institute of Technology, Japan) Alan W. Black awb@xxxxxxxxxx (Carnegie Mellon University, US) Simon King Simon.King@xxxxxxxx (The University of Edinburgh, UK) ======================================================================
Attachment:
CFP-Special_Issue_on_Statistical_Parametric_Speech_Synthesis.pdf
Description: Adobe PDF document