| Dear all National Institute of Informatics has an open postdoctoral research position in speech synthesis. Please circulate on your local mailing lists. Regards, Dr Junichi Yamagishi Associate Professor National Institute of Informatics ------------------------------------------------------------------------------------------------ Open postdoctoral research position, National Institute of Informatics, Tokyo, Japan http://www.nii.ac.jp/en/ Closing date: 13th December 2013 Duration: 12 months National Institute of Informatics and a collaboration project with NAVER National Institute of Informatics (NII) is an inter-university research institute, which underpins and promotes the creation of a state-of-the-art academic-information infrastructure that is essential to research and education within the broader academic community. The NII sound media group is an advanced research lab for sound, speech, and music media processing based at NII, Tokyo Japan. The post holder will work for a collaboration project funded by NAVER, Korea at NII and a key research aspect is vocoder and acoustic parameterization for statistical parametric speech synthesis. Job description In general, the representative work activities of the post holder are to support the principal investigator of the above project in achieving the goals under his direction. More specifically, the roles of the post holder are: • Taking responsibility for designing, building, developing and evaluating speech synthesis systems based on new acoustic parameterisation and vocoders. • Contributing to the project and collaborate with overseas cross-disciplinary project members. • Undertaking a specific role and taking responsibility for problem solving in the project under supervision. The research problems include the application of the proposed acoustic parameterisation such as speaker adaptation or voice conversion based on the new acoustic parameterisation. • Contributing to dissemination and publication of personal and/or research teams findings as appropriate. Knowledge, skills and experience • Degree in an appropriate field • PhD (or close to completion) • Experience in acoustic statistical modelling or in signal processing of speech The following criteria are not yes/no factors, but questions of degree. Recruitment will aim at selecting those candidates with the best possible performance in all these criteria. • Research experience in speech synthesis • Experience of the design, construction and evaluation of speech synthesis systems • Adaptation techniques for acoustic modelling, voice conversion techniques • Practical experience of applying machine learning • Knowledge of HMM and DNN • Research publications in international journals or conferences • Excellent programming skills • Familiarity with software tools including HTK, HTS, SPTK, and Festival • Ability to communicate complex information clearly, orally and in writing Salary JPY 300,000 - 400,000 per month, plus commuting allowance. The actual salary is according to experience and qualifications. Applications Please send the following four files by email to jyamagis@xxxxxxxxx (1) CV and publication records (2) PDF files of three representative papers (3) Research proposal (short summary of your past research and future plans) (4) Contact details of a referee Deadline 13th December 2013 ------------------------------------------------------------------------------------------------ |