Welcome to my website. I am an audio/speech technology developer and researcher. Currently, I am doing my PhD at the CSTR-University of Edinburgh, where I research on new signal representations and acoustic modelling for statistical parametric speech synthesis. Also, my interests cover a wide range of disciplines, such as Music, Digital Audio, real-time audio effects, Computer Programming, Acoustics, and so on. You will find on this website information about me, including education, publications, projects, trips, and especially the stuff that I love the most: Audio Technology Development !!

 

PUBLICATIONS

• S. Ronanki, M. S. Ribeiro, F. Espic, and O. Watts “The CSTR entry to the Blizzard Challenge 2017,” In Proc. Blizzard Challenge, Stockholm, Sweden, August, 2017. [pdf]

• F. Espic, C. Valentini-Botinhao, and S. King, “Direct Modelling of Magnitude and Phase Spectra for Statistical Parametric Speech Synthesis,” in Proc. Interspeech, Stockholm, Sweden, August, 2017. [pdf, demo and code]

• F. Espic, C. Valentini-Botinhao, Z. Wu, and S. King, “Waveform generation based on signal reshaping for statistical parametric speech synthesis,” in Proc. Interspeech, San Francisco, CA, USA, September, 2016. [pdf – democode]

• F. Villavicencio, J. Yamagishi, J. Bonada, and F. Espic, “Applying spectral normalisation and efficient envelope estimation and statistical transformation for the Voice Conversion Challenge 2016,” in Proc. Interspeech, San Francisco, CA, USA, September, 2016. [pdf]

• V. Poblete, F. Espic, S. King, R. M. Stern, F. Huenupan, J. Fredes, and N. Becerra Yoma, “A perceptually-motivated low-complexity instantaneous linear channel normalization technique applied to speaker verification,” Computer Speech and Language, Volume 31, Issue 1, Pages 1-27, 2015. [pdf]

• W. Hussein, S. M. Khan, J. Zamorano, F. Espic, and N. Becerra Yoma, “A novel ultrasound based technique for classifying gas bubble sizes in liquids,” Measurement Science and Technology, 25, no. 12, 2014. [pdf]

Other publications and talks:

•F. Espic, C. Valentini-Botinhao, and S. King,  “MagPhase Vocoder: Magnitude and phase analysis/synthesis for statistical parametric speech synthesis,” UK-Speech Conference, Cambridge, UK, September, 2017.

• S.King, O. Watts, S. Ronanki, Z. Wu, and  F. Espic “Tutorial: Deep Learning for Text-to-Speech Synthesis, using the Merlin toolkit,” Interspeech Conference, Stockholm, Sweden, August, 2017. [slides and videos]

• F. Espic, “A Survey About IFIR Filters and Their More Recent Improvements,” report, University of Miami, 2011. Cited in the book “Digital Signal Processing with Matlab Examples, Volume 1” by Jose Maria Giron-Sierra, Springer, 2017. [pdf]

• F. Espic, Talk on Waveform generation based on signal reshaping for statistical parametric speech synthesis. UK-Speech Conference, Sheffield, UK, June, 2016. Video of the presentation:

• F. Espic, “A Phrase Recognition System Intended for Musical Applications,” report, University of Miami, 2011. [pdf]

• F. Espic, “A Simple Music Transcription Method Using Comb Filter Techniques and Envelope Detection,” report, University of Miami, 2011.  [pdf]


CURRICULUM VITAE

You can visit my LinkedIn profile or email me to ask for a CV in pdf.


CONTACT

For any enquiry, question, suggestion, etc., just email me at: