Anton Ragni

Anton Ragni

Background - Projects - Research - Publications

Background - Projects - Research - Publications

Position: Research Associate

Position: Research Associate

E-mail: ar527 [at] cam.ac.uk

E-mail: ar527 [at] cam.ac.uk

Office Location: BE4-58

Office Location: BE4-58

Background

Background

I received my B.Eng. and M.Eng. degrees in information technology from University of Tartu in 2005 and 2007 respectively. From 2005 to 2008 I underwent graduate training at Nordic Graduate School of Language Technology. From 2007 to 2008 I was an intern in Speech Technology Group, Toshiba Research Europe Limited. From 2008 to 2014 I was studying for my PhD degree in automatic speech recognition at University of Cambridge, where my supervisor was Professor Mark Gales. I am now a Research Associate workin gfor Prof Gales on the BABEL project.

Received B.Eng. and M.Eng. degrees in information technology from University of Tartu in 2005 and 2007 respectively.

I received the "Best Student Paper Award" at IEEE Workshop on Automatic Speech Recognition and Understanding for my paper "Generative kernels for noise robust ASR" co-authored with M.J.F. Gales in 2011.

From 2005 to 2008 underwent graduate training at Nordic Graduate School of Language Technology.

From 2007 to 2008 was an intern in Speech Technology Group, Toshiba Research Europe Limited.

Since 2008 has been pursuing Ph.D. degree in automatic speech recognition at University of Cambridge.

Received "Best Student Paper Award" at IEEE Workshop on Automatic Speech Recognition and Understanding for his paper "Generative kernels for noise robust ASR" co-authored with M.J.F. Gales in 2011.

Projects

Projects

Currently associated with projects:

Currently associated with projects:

BABEL (IARPA funded)

BABEL (IARPA funded) Generative kernels and score-spaces for classification of speech (non-funded) HTK Version 3 (non-funded)

Generative kernels and score-spaces for classification of speech (non-funded)

HTK Version 3 (non-funded)

In past associated with projects:

In past associated with projects:

Discriminative models for speech (Toshiba, EPSRC and HTK funded PhD)

Discriminative models for speech (Toshiba, EPSRC and HTK funded PhD) HTK Version 3

HTK Version 3

In past collaborated on projects:

In past collaborated on projects:

Kernel Methods for Speech Processing (non-funded) with Z. Roupakia and M.J.F. Gales

Kernel Methods for Speech Processing (non-funded) with Z. Roupakia and M.J.F. Gales Structured Discriminative Models (non-funded) with S.-X. Zhang and M.J.F. Gales

Structured Discriminative Models (non-funded) with S.-X. Zhang and M.J.F. Gales

Research Interests

Research Interests

Kernel methods for speech processing: acoustic modelling and language modelling

Kernel methods for speech processing:

Discriminative modelling for speech processing: unstructured discriminative models and structured discriminative models

acoustic modelling language modelling

Generative modelling for speech processing: universal generative acoustic/language models and speaker/environmental adaptation/compensation

Discriminative modelling for speech processing:

unstructured discriminative models structured discriminative models

Generative modelling for speech processing:

universal generative acoustic/language models speaker/environmental adaptation/compensation

Publications

Publications