UCL Psychology and Language Sciences


Speech Science Forum 17rd June - Dr. Heiga Zen

17 June 2021, 10:00 am–11:00 am

Please join us at 10am on June 17rd for Dr. Heiga Zen's talk, "Model-based text-to-speech synthesis".

Event Information

Open to





Dr. Antony Scott Trotter – Speech, Hearing and Phonetic Science

Title: Model-based text-to-speech synthesis


Model-based text-to-speech (TTS) synthesis has advanced from traditional hidden Markov model (HMM)-based approach to a modern neural network-based one.  It has been a mainstream in TTS research, and many products based on it are now available.  This talk will cover its basics including the probabilistic formulation as well as implementations in the neural network-based approach.  The presenter's recent work will also be presented.

About the Speaker

Dr. Heiga Zen

Brain Team Researcher at Google

Heiga Zen received his AE from Suzuka National College of Technology, Suzuka, Japan, in 1999, and PhD from the Nagoya Institute of Technology, Nagoya, Japan, in 2006. He was an Intern/Co-Op researcher at the IBM T.J. Watson Research Center, Yorktown Heights, NY (2004--2005), and a Research Engineer at Toshiba Research Europe Ltd. Cambridge Research Laboratory, Cambridge, UK (2008--2011). At Google, he was in the Speech team from July 2011 to July 2018, then joined the Brain team from August 2018. His research interests include speech technology and machine learning. He was one of the original authors and the first maintainer of the HMM-based speech synthesis system (HTS).

More about Dr. Heiga Zen