University of Cambridge > Talks.cam > speech synthesis seminar series > STATISTICAL SPEECH SYNTHESIS

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

STATISTICAL SPEECH SYNTHESIS

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Kai Yu.

This talk will formulate the speech synthesis problem in a statistical framework and discuss how it is decomposed into its sub-problems, which include text analysis, spectral envelope estimation, acoustic model training, speech parameter generation, and waveform reconstruction. The talk will also describe how these sub-problems are solved in HMM -based speech synthesis. Some recent trials will also be discussed.

This talk is part of the speech synthesis seminar series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Cambridge Carbon Nanotechnology Society Proteomics as a tool in data driven systems biology cms-all@maths.cam.ac.uk

Other talks

Microtubule Modulation of Myocyte Mechanics How language variation contributes to reading difficulties and “achievement gaps” All-resolutions inference for brain imaging Protein targeting within the chloroplast: a cell-biological view of starch biosynthesis CANCELLED - Methodology Masterclass: Exploring the pedagogic possibilities of new diaspora formations and transnationalism. Part IIB Poster Presentations Coatable photovoltaics (Title t o be confirmed) Sneks long balus Formation and disease relevance of axonal endoplasmic reticulum, a "neuron within a neuron”. Protein Folding, Evolution and Interactions Symposium New methods for genetic analysis
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity