2015 Speech Processing Courses in Crete
Speech Synthesis: From Diphones to Modern Speech Synthesis Engines

27-31 July 2015    University of Crete, Heraklion, Crete, Greece


The Speech Processing Courses in Crete (SPCC) are targeting to teach graduate students and researchers the latest advancements of speech processing covering theory, hands on, and establishing contacts between the academics and industry. The school will provide the chance to students and professionals to meet world leaders in speech technology, exchanging ideas, sharing experiences and vision.
The Summer School is organized by the University of Crete, Greece. It is also sponsored by Toshiba, Google, National Institute of Informatics, Institute for Language and Speech Processing, and IBM. We thank our sponsors for their support.

For 2015, the school topic is: From Diphones to Modern Speech Synthesis Engines

The topic includes:
  • Speech Signal Modelling and Modifications
  • Acoustic Modelling: HMM, LDM, DNN
  • Approaches: Diphones, Unit Selection, Statistical, Hybrid
  • Listening Context Aware speech synthesis systems

Registration Info

Students: €300, Non-students: €450, to cover lunches, coffee breaks, banquet, school materials, bus transfer between city and campus. Limited number of places for highly motivated researchers and students, so reserve your position soon (yannis@csd.uoc.gr).


Participants, if they wish, are expected to present their work as a poster (119cm width x 97cm height, at most), during 1 hour in each day (at the mid of each school day). Theory will be followed by hands on sessions while speech synthesis systems will be demonstrated by the lecturers during the last day of the school. There will be an award for the best student poster which will be announced during the last day (closing ceremony).

School Poster

You can download the school poster here!

Best Student Poster Winners

  • 1st winner: Thomas Merritt, University of Edinburgh, UK, "Deep Neural Network Context Embeddings For Model Selection In Rich-Context HMM Synthesis"
  • 2nd winner: Maria Koutsogiannaki, University of Crete, Greece, "Speech Intelligibility Enhancement based on Clear Speech Properties"
  • 3rd winner: Sam Ribeiro, University of Edinburgh, UK, "Multi-Level Representation of f0 using the Discrete Cosine Transform and the Continuous Wavelet Transform"