>
TCTS Lab Staff
 
 



Maria ASTRINAKI

[Groups] [Publications]

Researcher, PhD  

University of Mons (UMONS) 
Engineering Faculty of Mons (FPMs) 

Numediart Research Institute  
Infortech Research Institute  
TCTS Lab  
31, Boulevard Dolez  
B-7000 Mons (Belgium)  

phone: +32 65 37 47 31  
fax: +32 65 374729  
maria.astrinaki


Maria Astrinaki graduated from the Computer Science Department, University Of Crete, Greece, in 2007. She performed her Master's Thesis in the same department in the field of Voice Pathology Detection (July 2010).

She defended her PhD thesis in applied sciences at the University of Mons in October 2014. The thesis focuses in bringing interactive designs in the context of HMM-based speech synthesis. Many applications and proof of concept examples that enable the user interaction over all the production levels in realtime were developed.

She was the initiator and leader of the Mage project, an open source library for performative HMM-based synthesis.

Her research interests focus on interactive designs, software development and architecture, signal processing theory and its applications to speech processing, especially speech synthesis.

Groups :

^ Top ^   

Publications :

PhD Dissertation

2014
M. ASTRINAKI, 2014, "Performative Statistical Parametric Speech Synthesis Applied to Interactive Designs", PhD thesis supervised by Prof. T. Dutoit and Dr. N. D'Alessandro, October 2014.

Papers in Conference Proceedings

2014
J. TILMANNE, N. D'ALESSANDRO, M. ASTRINAKI, T. RAVET, 2014, "Exploration of a Stylistic Motion Space Through Realtime Synthesis", in Proceedings of the 9th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2014), Special Session on ICT-based Analysis and Modeling of Intangible Cultural Heritage (IAMICH 2014), Lisbon, Portugal, January 5-8.
J. TILMANNE, N. D'ALESSANDRO, T. RAVET, M. ASTRINAKI, A. MOINET, 2014, "Full-Body Gait Reconstruction Using Covariance-Based Mapping Within a Realtime HMM-based Framework", in Proceedings of the 50th annual convention of the AISB (AISB-50), pp. 313-316, London, UK, April 1-4.
2013
C. VEAUX, M. ASTRINAKI, K. OURA, A. J. R. CLARK, J. YAMAGISHI, 2013, "Gesture Control of HMM-Based Singing Voice Synthesis", 8th Speech Synthesis Workshop (SSW8), pp. 247-248 , Barcelona, Spain, August 31 - September 2.
M. ASTRINAKI, A. MOINET, J. YAMAGISHI, K. RICHMOND, Z.-H. LING, S. KING, T. DUTOIT, 2013, "MAGE - Reactive articulatory feature control of HMM-based parametric speech synthesis", 8th Speech Synthesis Workshop (SSW8), p. 243 (poster paper), Barcelona, Spain, August 31 - September 2.
M. ASTRINAKI, A. MOINET, J. YAMAGISHI, K. RICHMOND, Z.-H. LING, S. KING, T. DUTOIT, 2013, "MAGE - Reactive articulatory feature control of HMM-based parametric speech synthesis", 8th Speech Synthesis Workshop (SSW8), pp. 207-212 , Barcelona, Spain, August 31 - September 2.
M. ASTRINAKI, N. D'ALESSANDRO, L. REBOURSIERE, A. MOINET, T. DUTOIT, 2013, "Mage 2.0: New features and its application in the development of a talking guitar", Proceedings of the 13th Conference on New Interfaces for Musical Expression (NIME'13), Daejeon + Seoul, Korea Republic, May 27-30.
N. D'ALESSANDRO, M. ASTRINAKI, T. DUTOIT, 2013, "MAGEFACE : Performative Convension of Facial Characteristics into Speech Synthesis Parameters", Proceedings of the 5th International Conference on Intelligent Technologies for Interactive Entertainment (INTETAIN 2013), Mons, Belgium, July 3-5.
M. ASTRINAKI, A. MOINET, N. D'ALESSANDRO, T. DUTOIT, 2013, "Pure Data External for Reactive HMM-based Speech and Singing Synthesis", Proceedings of the 16th International Conference on Digital Audio Effects (DAFx-13), pp. 78-81, Maynooth, Ireland, September 2-5.
M. ASTRINAKI, J. YAMAGISHI, N. D'ALESSANDRO, T. DUTOIT, 2013, "Reactive accent interpolation through an interactive map application", 8th Speech Synthesis Workshop (SSW8), p. 245, Barcelona, Spain, August 31 - September 2.
M. ASTRINAKI, J. YAMAGISHI, S. KING, N. D'ALESSANDRO, T. DUTOIT, 2013, "Reactive accent interpolation through an interactive map application", Proceedings of the 14th Conference of the International Speech Communication Association (Interspeech 2013), Lyon, France, August 25-29.
N. D'ALESSANDRO, J. TILMANNE, M. ASTRINAKI, T. HUEBER, R. DALL, T. RAVET, A. MOINET, H. ÇAKMAK, O. BABACAN, A. BARBULESCU, V. PARFAIT, V. HUGUENIN, E. S. KALAYCI, Q. HU, 2013, "Reactive Statistical Mapping: Towards the Sketching of Performative Control with Data", Proceedings of the 9th International Summer Workshop on Multimodal Interfaces - eNTERFACE'13, in Innovative and Creative Developments in Multimodal Interaction Systems - IFIP Advances in Information and Communication Technology (IFIP AICT), Volume 425, pp. 20-49, Lisbon, Portugal, July 15 - August 9, doi:10.1007/978-3-642-55143-7_2.
2012
M. ASTRINAKI, L. REBOURSIERE, A. MOINET, R. GRAHAM, N. D'ALESSANDRO, T. DUTOIT, 2012, "Is This Guitar Talking or What !?", Proceedings of the 8th International Summer Workshop on Multimodal Interfaces - eNTERFACE'12, pp. 47-55, July, Metz, France.
M. ASTRINAKI, N. D'ALESSANDRO, T. DUTOIT, 2012, "MAGE - A Platform for Tangible Speech Synthesis", Proceedings of the 12th Conference on New Interfaces for Musical Expression (NIME'12), pp. 353-356, Ann Arbor, Michigan, USA, May 21-23, 2012.
M. ASTRINAKI, N. D'ALESSANDRO, B. PICART, T. DRUGMAN, T. DUTOIT, 2012, "Reactive and Continuous Control of HMM-based Speech Synthesis", IEEE Workshop on Spoken Language Technology (SLT 2012), Miami, Florida, USA, December 2-5.
2011
M. ASTRINAKI, O. BABACAN, N. D'ALESSANDRO, T. DUTOIT, S. FELS, 2011, "MAGE / pHTS in Collaborative Vocal Puppetry (CoVoP) - Multi-User Performative HMM-based Voice Synthesis on Distributed Platforms", Proceedings of the 7th International Summer Workshop on Multimodal Interfaces - eNTERFACE'11, Plzeň (Pilsen), Czech Republic, August 1-26.
M. ASTRINAKI, O. BABACAN, N. D'ALESSANDRO, T. DUTOIT, 2011, "sHTS: A Streaming Architecture for Statistical Parametric Speech Synthesis", First International Workshop on Performative Speech and Singing Synthesis (p3s-2011), March 14-15, Vancouver, BC, Canada.

Technical Reports

2013
A. J. R. CLARK, M. A. KONKIEWICZ, M. ASTRINAKI, J. YAMAGISHI, 2013, "Reactive Control of Expressive Speech Synthesis Using Kinect Skeleton Tracking", in IPSJ SIG Technical Report.
2012
M. ASTRINAKI, N. D'ALESSANDRO, T. DUTOIT, 2012, "MageFaceOSC: Performative Speech Synthesis Based On Realtime Face Tracking", QPSR of the numediart research program, volume 5, n° 1, March 2012, pp. 15–16.
N. D'ALESSANDRO, O. BABACAN, M. ASTRINAKI, J. WANG, 2012, "PEACH: an Optimized Framework for Performative Pitch-Synchronous Overlap-Add Sound Synthesis Using Point-Cloud Visualization", QPSR of the numediart research program, volume 5, n° 4, pp. 85-87, December 2012.
2011
M. ASTRINAKI, O. BABACAN, N. D'ALESSANDRO, T. DUTOIT, S. FELS, 2011, "MAGE / pHTS in Collaborative Vocal Puppetry (CoVoP) - Multi-User Performative HMM-based Voice Synthesis on Distributed Platforms", QPSR of the numediart research program, volume 4, n° 3, September 2011, pp. 59-64.
M. ASTRINAKI, O. BABACAN, N. D'ALESSANDRO, B. PICART, T. DUTOIT, 2011, "pHTS for Max/MSP: A Stream­ing Archi­tec­ture for Sta­tis­ti­cal Para­met­ric Speech Syn­the­sis", QPSR of the numediart research program, volume 4, n° 1, pp. 7-11, March 2011.
2010
J.A. MILLS III, M. ASTRINAKI, R. CHESSINI BOSE, L. REBOURSIERE, T. TODOROFF, 2010, "Aug­mented Con­duc­tor", QPSR of the numediart research program, volume 3, n° 4, pp 71-76, December 2010.

^ Top ^