Department of Engineering

Machine Intelligence Laboratory

Matt Shannon

Matt Shannon

Position: PhD student in statistical speech synthesis

Email: sms46 AT cam ac uk

Supervisor: Prof Bill Byrne

Research

Acoustic modelling for statistical speech synthesis. For the first part of my PhD I was part of the EMIME (Effective Multilingual Interaction in Mobile Environments) project for personalized speech synthesis. I am currently part of the EPSRC Natural Speech Technology project.

Data

  • REHASP 0.5
    A corpus of repeated speech. This corpus contains 1200 utterances (30 sentences, each repeated 40 times) from a female native British English talker. Having the same text read aloud multiple times may be useful for various purposes, for example to distinguish different sources of variability in the speech signal. Our Interspeech 2014 paper used this corpus to investigate various common modelling assumptions.
    [ REHASP 0.5 on Edinburgh DataShare ]

Software

Journal papers

Conference papers

Technical reports

  • M. Shannon and W. Byrne (2013)
    Partially analytic speech parameter generation considering global variance
    Department of Engineering, University of Cambridge, UK
    Technical Report CUED/F-INFENG/TR.682
    (to appear; a preliminary version can be obtained by emailing me)
  • M. Shannon and W. Byrne (2012)
    Viewing the trajectory HMM as a generalized autoregressive HMM
    Department of Engineering, University of Cambridge, UK
    Technical Report CUED/F-INFENG/TR.677
    (to appear; a preliminary version can be obtained by emailing me)
  • M. Shannon and W. Byrne (2009)
    A formulation of the autoregressive HMM for speech synthesis
    Department of Engineering, University of Cambridge, UK
    Technical Report CUED/F-INFENG/TR.629
    [ pdf ]

Theses

Other talks and posters

Teaching

Contact information

Baker Building, BE5-02
Engineering Department
Trumpington Street, Cambridge
CB2 1PZ, United Kingdom