HMM-based Speech Synthesis with an Acoustic Glottal Source Model

Javier Cabral, Steve Renals, Korin Richmond, Junichi Yamagishi

Research output: Chapter in Book/Report/Conference proceedingConference contribution


A major cause of degradation of speech quality in HMM-based speech synthesis is the use of a simple delta pulse signal to generate the excitation of voiced speech. This paper describes a new approach to using an acoustic glottal source model in HMM-based synthesisers. The goal is to improve speech quality and parametric flexibility to better model and transform voice characteristics.
Original languageEnglish
Title of host publicationProc. The First Young Researchers Workshop in Speech Technology
Publication statusPublished - 2009


Dive into the research topics of 'HMM-based Speech Synthesis with an Acoustic Glottal Source Model'. Together they form a unique fingerprint.

Cite this