Education

SPCC

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.

2017

• webpage: http://spcc.csd.uoc.gr/
• the school topic is: Towards Intelligible and Conversational Speech Synthesis Engines, The topic includes:
  • Modern Acoustic Modelling Approaches (DNN/LSTM, WaveNet)
  • Text Normalization and Linguistic Analysis
  • Prosody
  • Advanced Vocoders and Modifications (Voice Conversion)
  • Intelligibility and Cognitive Effort in Speech Synthesis

2016

• webpage: http://spcc.csd.uoc.gr/SPCC2016/
• the school topic is: Advancements in Modern Speech Synthesis Engines, The topic includes:
  • Advanced Speech Signal Modelling and Modifications
  • Current Acoustic Modelling Approaches
  • Challenges in Fornt-End Processing
  • Listening Context Aware Speech Synthesis Systems
  • Text Normalization and Linguistic Analysis

Lecture slides used for SPCC 2016 are available online

• Dr. Yannis Agiomyrgiannakis, Google UK : Vocaine the Vocoder
• Prof. Yannis Stylianou, University of Crete : Adaptive Sinusoidal Models
• Prof. Yannis Stylianou, University of Crete : Sinusoidal Modeling
• Prof. Simon King, University of Edinburgh : Text Processing for Speech Synthesis
• Dr. Spyros Raptis, ILSP Athena : Unit-Selection-based Text-To-Speech Synthesis
• Prof. Simon King, University of Edinburgh : Speech Synthesis with Hidden Markov Models
• Dr. Vassilis Tsiaras, University of Crete : Linear Dynamical Models in Speech Synthesis
• Dr. Yannis Agiomyrgiannakis, Google UK : Vocoder-side Voice Morphing for TTS
• Dr. Heiga Zen, Google UK : Artificial Neural Network based Speech Synthesis
• Dr. Masami Akamine, Toshiba Japan : Closed Loop Diphone-based Text-To-Speech Synthesis
• Prof. Yannis Stylianou, University of Crete : Speech Intelligibility
• Prof. Simon King, University of Edinburgh : Evaluating Speech Synthesis
• Prof. Simon King, University of Edinburgh : Hybrid Speech Synthesis

2015

• webpage: http://spcc.csd.uoc.gr/SPCC2015/
• 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

2014

• webpage: http://spcc.csd.uoc.gr/SPCC2014/

Keynotes & tutorials

• Simon King - EUSIPCO keynote

• Deep Learning for Text-to-Speech Synthesis, using the Merlin toolkit @ Interspeech 2017

• ISCA Medalist: For leadership and extensive contributions to speech and language processing @ Interspeech 2016

• Voice conversion and spoofing countermeasures for speaker verification @ Odyssey 2016

• Understanding individual-level speech variability: From novel speech production data to robust speaker recognition

• Deep Learning for Speech Generation and Synthesis @ ISCSLP 2014

• Speaking in adverse conditions: from behavioural observations to intelligibility-enhancing speech modifications @ Odyssey 2014

Other kind of teaching materials

• Simon King's course website

• An introductory course on speech processing (in French and English) by Thierry Dutoit, , Faculté Polytechnique de Mons, Belgium.

• TTSBOX, A Matlab tutorial toolbox on corpus-based Text-to-Speech synthesis, by Thierry Dutoit, Faculté Polytechnique de Mons, Belgium.

Samples

• Access to some speech samples

Educational Softwares

• See our list of educational softwares

Historical images

Take a look at our gallery of historical images.

External Links

• See our external references page
• Dennis Klatt's History of Speech Synthesis,
• Examples of Synthesized Speech,
• "The Talking Computer": Text to Speech Synthesis (J.P. Olive in Hal's Legacy, MITPress),
• German-TTS and emotional synthesis ([1] and [2]) demo by Felix Burkhardt.