An engineering blog for engineers working in Audiovisuals, Telecommunications, Electronics, ICT, Computer Engineering, Multimedia and Telematics.

26 July 2010 | Posted by Redacción Ingeniería

New PhD thesis presented on HMM-based speech synthesis

Last Friday July 16th a new PhD thesis was presented within the research group on media technologies, the author of the thesis is Xavier Gonzalvo and the title is "HMM-based speech synthesis applied to Spanish and English, its applications and a hybrid approach". The advisors of this work are Dr. Joan Claudi Socoró and Dr. Ignasi Iriondo. We congratulate all for this excellent work! Abstract: This work presents a Text-to-Speech (TTS) system based in a statistical framework using Hidden Markov Models (HMMs) that will deal with the main topics uder study in recent years such as voice style adaptation, trainable TTS systems and low print databases. Moreover, a cutting edge hybrid approach combining concatenative and statistical synthesis is also presented. Ideas and results in this work show a step forward in the HMM-based TTS system field.

Share