Christian Weiss

From L²F

Christian Weiss


Christian Weiss received a M.A. in Computational Linguistics, Sociology and Computer Science from University of Heidelberg, Germany in 2002 and a PhD from University of Bonn, Germany in 2006. He did his PhD studies at Institute for Communication Research, from 2002 to 2006 in the group of Prof. Dr. W. Hess. His PhD thesis was on "Adaptive Audio-Visual Synthesis" covering statistical learning for video-realistic audio visual synthesis. He was working in a German Research Foundation DFG granted project on automatic training strategies for unit-selection based speech synthesis and was a DAAD/JSPS Fellow in 2005 at the Nagoya Institute of Technology, Japan Nitech. Previous he worked for IBM European Speech Research. He is a member of GI and ISCA.

INESC ID Information

Publications

International Conferences

2007

  • Christian Weiss, Luís C. Oliveira, Sérgio Paulo, Carlos Miguel Duarte Mendes, Luís António Dias Mestre Figueira, Marco Vala, Pedro Sequeira, Ana Paiva, Thurid Vogt, Elisabeth Andre, ECIRCUS: Building Voices for Autonomous Speaking Agents, In 6th Speech Synthesis Workshop, ISCA, Bonn, August 2007

2006

  • Christian Weiss, Wolfgang Hess, Conditional Random Fields for Hierarchical Segment Selection in TTS, In ICSLP 2006, series 9, Pittsburgh, USA, September 2006
  • Christian Weiss, Wolfgang Hess, CRF's for Acoustic Segement-Selection: A Case Study, In Advances in Speech Technology, series 13, Maribor, Slovenia, July 2006

National Conferences

2006

  • Christian Weiss, Maria Joao Barros, Maximum Entropy motivated Grapheme-to-Phoneme, Stress and Syllable Boundary Prediction for Portuguese Text-to-Speech, In Technologia del Hablas, series 5, Zaragosa, Spain, November 2006

Research Interests

  • Speech synthesis
  • Audio-visual synthesis
  • Statistical learning